To see the other types of publications on this topic, follow the link: Unknown classes detection (Open-Set Recognition).
Journal articles on the topic 'Unknown classes detection (Open-Set Recognition)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Unknown classes detection (Open-Set Recognition).'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Xu, Baile, Furao Shen, and Jian Zhao. "Contrastive Open Set Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 9 (June 26, 2023): 10546–56. http://dx.doi.org/10.1609/aaai.v37i9.26253.
Full textAbstract:
In conventional recognition tasks, models are only trained to recognize learned targets, but it is usually difficult to collect training examples of all potential categories. In the testing phase, when models receive test samples from unknown classes, they mistakenly classify the samples into known classes. Open set recognition (OSR) is a more realistic recognition task, which requires the classifier to detect unknown test samples while keeping a high classification accuracy of known classes. In this paper, we study how to improve the OSR performance of deep neural networks from the perspective of representation learning. We employ supervised contrastive learning to improve the quality of feature representations, propose a new supervised contrastive learning method that enables the model to learn from soft training targets, and design an OSR framework on its basis. With the proposed method, we are able to make use of label smoothing and mixup when training deep neural networks contrastively, so as to improve both the robustness of outlier detection in OSR tasks and the accuracy in conventional classification tasks. We validate our method on multiple benchmark datasets and testing scenarios, achieving experimental results that verify the effectiveness of the proposed method.
2
Xia, Ziheng, Penghui Wang, and Hongwei Liu. "Radar HRRP Open Set Target Recognition Based on Closed Classification Boundary." Remote Sensing 15, no. 2 (January 12, 2023): 468. http://dx.doi.org/10.3390/rs15020468.
Full textAbstract:
Radar automatic target recognition based on high-resolution range profile (HRRP) has become a research hotspot in recent years. The current works mainly focus on closed set recognition, where all the test samples are assigned to the training classes. However, radar may capture many unknown targets in practical applications, and most current methods are incapable of identifying the unknown targets as the ’unknown’. Therefore, open set recognition is proposed to solve this kind of recognition task. This paper analyzes the basic classification principle of both recognitions and makes sure that determining the closed classification boundary is the key to addressing open set recognition. To achieve this goal, this paper proposes a novel boundary detection algorithm based on the distribution balance property of k-nearest neighbor objects, which can be used to realize the identification of the known and unknown targets simultaneously by detecting the boundary of the known classes. Finally, extensive experiments based on measured HRRP data have demonstrated that the proposed algorithm is indeed helpful to greatly improve the open set performance by determining the closed classification boundary of the known classes.
3
Halász, András Pál, Nawar Al Hemeary, Lóránt Szabolcs Daubner, Tamás Zsedrovits, and Kálmán Tornai. "Improving the Performance of Open-Set Recognition with Generated Fake Data." Electronics 12, no. 6 (March 9, 2023): 1311. http://dx.doi.org/10.3390/electronics12061311.
Full textAbstract:
Open-set recognition models, in addition to generalizing to unseen instances of known categories, have to identify samples of unknown classes during the training phase. The main reason the latter is much more complicated is that there is very little or no information about the properties of these unknown classes. There are methodologies available to handle the unknowns. One possible method is to construct models for them by using generated inputs labeled as unknown. Generative adversarial networks are frequently deployed to generate synthetic samples representing unknown classes to create better models for known classes. In this paper, we introduce a novel approach to improve the accuracy of recognition methods while reducing the time complexity. Instead of generating synthetic input data to train neural networks, feature vectors are generated using the output of a hidden layer. This approach results in a less complex structure for the neural network representation of the classes. A distance-based classifier implemented by a convolutional neural network is used in our implementation. Our solution’s open-set detection performance reaches an AUC value of 0.839 on the CIFAR-10 dataset, while the closed-set accuracy is 91.4%, the highest among the open-set recognition methods. The generator and discriminator networks are much smaller when generating synthetic inner features. There is no need to run these samples through the first part of the classifier with the convolutional layers. Hence, this solution not only gives better performance than generating samples in the input space but also makes it less expensive in terms of computational complexity.
4
Zhang, Yuhang, Yue Yao, Xuannan Liu, Lixiong Qin, Wenjing Wang, and Weihong Deng. "Open-Set Facial Expression Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 1 (March 24, 2024): 646–54. http://dx.doi.org/10.1609/aaai.v38i1.27821.
Full textAbstract:
Facial expression recognition (FER) models are typically trained on datasets with a fixed number of seven basic classes. However, recent research works (Cowen et al. 2021; Bryant et al. 2022; Kollias 2023) point out that there are far more expressions than the basic ones. Thus, when these models are deployed in the real world, they may encounter unknown classes, such as compound expressions that cannot be classified into existing basic classes. To address this issue, we propose the open-set FER task for the first time. Though there are many existing open-set recognition methods, we argue that they do not work well for open-set FER because FER data are all human faces with very small inter-class distances, which makes the open-set samples very similar to close-set samples. In this paper, we are the first to transform the disadvantage of small inter-class distance into an advantage by proposing a new way for open-set FER. Specifically, we find that small inter-class distance allows for sparsely distributed pseudo labels of open-set samples, which can be viewed as symmetric noisy labels. Based on this novel observation, we convert the open-set FER to a noisy label detection problem. We further propose a novel method that incorporates attention map consistency and cycle training to detect the open-set samples. Extensive experiments on various FER datasets demonstrate that our method clearly outperforms state-of-the-art open-set recognition methods by large margins. Code is available at https://github.com/zyh-uaiaaaa.
5
Zhou, Yu, Song Shang, Xing Song, Shiyu Zhang, Tianqi You, and Linrang Zhang. "Intelligent Radar Jamming Recognition in Open Set Environment Based on Deep Learning Networks." Remote Sensing 14, no. 24 (December 8, 2022): 6220. http://dx.doi.org/10.3390/rs14246220.
Full textAbstract:
Jamming recognition is an essential step in radar detection and anti-jamming in the complex electromagnetic environment. When radars detect an unknown type of jamming that does not occur in the training set, the existing radar jamming recognition algorithms fail to correctly recognize it. However, these algorithms can only recognize this type of jamming as one that already exists in our jamming library. To address this issue, we present two models for radar jamming open set recognition (OSR) that can accurately classify known jamming and distinguish unknown jamming in the case of small samples. The OSR model based on the confidence score can distinguish known jamming from unknown jamming by assessing the reliability of the sample output probability distribution and setting thresholds. Meanwhile, the OSR model based on OpenMax can output the probability of jamming belonging to not only all known classes but also unknown classes. Experimental results show that the two OSR models exhibit high recognition accuracy for known and unknown jamming and play a vital role in sensing complex jamming environments.
6
Vázquez-Santiago, Diana-Itzel, Héctor-Gabriel Acosta-Mesa, and Efrén Mezura-Montes. "Vehicle Make and Model Recognition as an Open-Set Recognition Problem and New Class Discovery." Mathematical and Computational Applications 28, no. 4 (July 3, 2023): 80. http://dx.doi.org/10.3390/mca28040080.
Full textAbstract:
One of the main limitations of traditional neural-network-based classifiers is the assumption that all query data are well represented within their training set. Unfortunately, in real-life scenarios, this is often not the case, and unknown class data may appear during testing, which drastically weakens the robustness of the algorithms. For this type of problem, open-set recognition (OSR) proposes a new approach where it is assumed that the world knowledge of algorithms is incomplete, so they must be prepared to detect and reject objects of unknown classes. However, the goal of this approach does not include the detection of new classes hidden within the rejected instances, which would be beneficial to increase the model’s knowledge and classification capability, even after training. This paper proposes an OSR strategy with an extension for new class discovery aimed at vehicle make and model recognition. We use a neuroevolution technique and the contrastive loss function to design a domain-specific CNN that generates a consistent distribution of feature vectors belonging to the same class within the embedded space in terms of cosine similarity, maintaining this behavior in unknown classes, which serves as the main guide for a probabilistic model and a clustering algorithm to simultaneously detect objects of new classes and discover their classes. The results show that the presented strategy works effectively to address the VMMR problem as an OSR problem and furthermore is able to simultaneously recognize the new classes hidden within the rejected objects. OSR is focused on demonstrating its effectiveness with benchmark databases that are not domain-specific. VMMR is focused on improving its classification accuracy; however, since it is a real-world recognition problem, it should have strategies to deal with unknown data, which has not been extensively addressed and, to the best of our knowledge, has never been considered from an OSR perspective, so this work also contributes as a benchmark for future domain-specific OSR.
7
Cai, Jiarui, Yizhou Wang, Hung-Min Hsu, Jenq-Neng Hwang, Kelsey Magrane, and Craig S. Rose. "LUNA: Localizing Unfamiliarity Near Acquaintance for Open-Set Long-Tailed Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 131–39. http://dx.doi.org/10.1609/aaai.v36i1.19887.
Full textAbstract:
The predefined artificially-balanced training classes in object recognition have limited capability in modeling real-world scenarios where objects are imbalanced-distributed with unknown classes. In this paper, we discuss a promising solution to the Open-set Long-Tailed Recognition (OLTR) task utilizing metric learning. Firstly, we propose a distribution-sensitive loss, which weighs more on the tail classes to decrease the intra-class distance in the feature space. Building upon these concentrated feature clusters, a local-density-based metric is introduced, called Localizing Unfamiliarity Near Acquaintance (LUNA), to measure the novelty of a testing sample. LUNA is flexible with different cluster sizes and is reliable on the cluster boundary by considering neighbors of different properties. Moreover, contrary to most of the existing works that alleviate the open-set detection as a simple binary decision, LUNA is a quantitative measurement with interpretable meanings. Our proposed method exceeds the state-of-the-art algorithm by 4-6% in the closed-set recognition accuracy and 4% in F-measure under the open-set on the public benchmark datasets, including our own newly introduced fine-grained OLTR dataset about marine species (MS-LT), which is the first naturally-distributed OLTR dataset revealing the genuine genetic relationships of the classes.
8
You, Jie, and Joonwhoan Lee. "Open-Set Recognition of Pansori Rhythm Patterns Based on Audio Segmentation." Applied Sciences 14, no. 16 (August 6, 2024): 6893. http://dx.doi.org/10.3390/app14166893.
Full textAbstract:
Pansori, a traditional Korean form of musical storytelling, is characterized by performances involving a vocalist and a drummer. It is well-known for the singer’s expressive narrative (aniri) and delicate gesture with fan in hand. The classical Pansori repertoires mostly tell love, satire, and humor, as well as some social lessons. These performances, which can extend from three to five hours, necessitate that the vocalist adheres to precise rhythmic structures. The distinctive rhythms of Pansori are crucial for conveying both the narrative and musical expression effectively. This paper explores the challenge of open-set recognition, aiming to efficiently identify unknown Pansori rhythm patterns while applying the methodology to diverse acoustic datasets, such as sound events and genres. We propose a lightweight deep learning-based encoder–decoder segmentation model, which employs a 2-D log-Mel spectrogram as input for the encoder and produces a frame-based 1-D decision along the temporal axis. This segmentation approach, processing 2-D inputs to classify frame-wise rhythm patterns, proves effective in detecting unknown patterns within time-varying sound streams encountered in daily life. Throughout the training phase, both center and supervised contrastive losses, along with cross-entropy loss, are minimized. This strategy aimed to create a compact cluster structure within the feature space for known classes, thereby facilitating the recognition of unknown rhythm patterns by allocating ample space for their placement within the embedded feature space. Comprehensive experiments utilizing various datasets—including Pansori rhythm patterns (91.8%), synthetic datasets of instrument sounds (95.1%), music genres (76.9%), and sound datasets from DCASE challenges (73.0%)—demonstrate the efficacy of our proposed method to detect unknown events, as evidenced by the AUROC metrics.
9
Ci, Wenyan, Tianxiang Xu, Runze Lin, and Shan Lu. "A Novel Method for Unexpected Obstacle Detection in the Traffic Environment Based on Computer Vision." Applied Sciences 12, no. 18 (September 6, 2022): 8937. http://dx.doi.org/10.3390/app12188937.
Full textAbstract:
Obstacle detection is the basis for the Advanced Driving Assistance System (ADAS) to take obstacle avoidance measures. However, it is a very essential and challenging task to detect unexpected obstacles on the road. To this end, an unexpected obstacle detection method based on computer vision is proposed. We first present two independent methods for the detection of unexpected obstacles: a semantic segmentation method that can highlight the contextual information of unexpected obstacles on the road and an open-set recognition algorithm that can distinguish known and unknown classes according to the uncertainty degree. Then, the detection results of the two methods are input into the Bayesian framework in the form of probabilities for the final decision. Since there is a big difference between semantic and uncertainty information, the fusion results reflect the respective advantages of the two methods. The proposed method is tested on the Lost and Found dataset and evaluated by comparing it with the various obstacle detection methods and fusion strategies. The results show that our method improves the detection rate while maintaining a relatively low false-positive rate. Especially when detecting unexpected long-distance obstacles, the fusion method outperforms the independent methods and keeps a high detection rate.
10
Dale, John M., and Leon N. Klatt. "Principal Component Analysis of Diffuse Near-Infrared Reflectance Data from Paper Currency." Applied Spectroscopy 43, no. 8 (November 1989): 1399–405. http://dx.doi.org/10.1366/0003702894204470.
Full textAbstract:
Product tampering and product counterfeiting are increasing the need for methods to quickly determine product authenticity. One of the concepts that we are investigating for the detection of counterfeit objects involves the use of pattern recognition techniques to analyze multivariant data acquired from properties intrinsic to the object. The near-infrared reflectance spectra of currency and other paper stock were used as a test system. The sample population consisted of authentic currency, circulated and uncirculated, and cotton and rag paper stock as stand-ins for counterfeit currency. Reflectance spectra were obtained from a spot that was essentially void of printing on both sides of the currency specimens. Although the reflectance spectra for all of the samples were very similar, principal component analysis separated the samples into distinct classes without there being any prior knowledge of their chemical or physical properties. Class separation was achieved even for currency bills that differed only in their past environment. Leave-One-Out procedures resulted in 100% correct classification of each member of the sample set. A K-Nearest-Neighbor test or a linear discriminate can be used to correctly classify unknown samples.
11
Jleed, Hitham, and Martin Bouchard. "Incremental multiclass open-set audio recognition." International Journal of Advances in Intelligent Informatics 8, no. 2 (July 31, 2022): 251. http://dx.doi.org/10.26555/ijain.v8i2.812.
Full textAbstract:
Incremental learning aims to learn new classes if they emerge while maintaining the performance for previously known classes. It acquires useful information from incoming data to update the existing models. Open-set recognition, however, requires the ability to recognize examples from known classes and reject examples from new/unknown classes. There are two main challenges in this matter. First, new class discovery: the algorithm needs to not only recognize known classes but it must also detect unknown classes. Second, model extension: after the new classes are identified, the model needs to be updated. Focusing on this matter, we introduce incremental open-set multiclass support vector machine algorithms that can classify examples from seen/unseen classes, using incremental learning to increase the current model with new classes without entirely retraining the system. Comprehensive evaluations are carried out on both open set recognition and incremental learning. For open-set recognition, we adopt the openness test that examines the effectiveness of a varying number of known/unknown labels. For incremental learning, we adapt the model to detect a single novel class in each incremental phase and update the model with unknown classes. Experimental results show promising performance for the proposed methods, compared with some representative previous methods.
12
Li, Chaohua, Enhao Zhang, Chuanxing Geng, and Songcan Chen. "All Beings Are Equal in Open Set Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 12 (March 24, 2024): 13446–54. http://dx.doi.org/10.1609/aaai.v38i12.29247.
Full textAbstract:
In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given K known classes as an additional K+1-th class to explicitly model potential open space. However, treating unknown classes without distinction is unequal for them relative to known classes due to the category-agnostic and scale-agnostic of the unknowns. This inevitably not only disrupts the inherent distributions of unknown classes but also incurs both class-wise and instance-wise imbalances between known and unknown classes. Ideally, the OSR problem should model the whole class space as K+∞, but enumerating all unknowns is impractical. Since the core of OSR is to effectively model the boundaries of known classes, this means just focusing on the unknowns nearing the boundaries of targeted known classes seems sufficient. Thus, as a compromise, we convert the open classes from infinite to K, with a novel concept Target-Aware Universum (TAU) and propose a simple yet effective framework Dual Contrastive Learning with Target-Aware Universum (DCTAU). In details, guided by the targeted known classes, TAU automatically expands the unknown classes from the previous 1 to K, effectively alleviating the distribution disruption and the imbalance issues mentioned above. Then, a novel Dual Contrastive (DC) loss is designed, where all instances irrespective of known or TAU are considered as positives to contrast with their respective negatives. Experimental results indicate DCTAU sets a new state-of-the-art.
13
Васильева, Ирина Карловна, and Анатолий Владиславович Попов. "МЕТОД СИНТЕЗА МНОГОКОМПОНЕНТНОЙ МОДЕЛИ АТРИБУТИВНЫХ ПРИЗНАКОВ ОБЪЕКТОВ." RADIOELECTRONIC AND COMPUTER SYSTEMS, no. 2 (October 8, 2018): 13–25. http://dx.doi.org/10.32620/reks.2018.2.02.
Full textAbstract:
The subject matter of the article are the processes of forming of objects’ attribute features analytical descriptions for solving applied problems of statistical recognition of objects’ images on multi-channel images. The goal is to develop a multicomponent mathematical model for representing statistical information about the summation of geometric, colour and structural parameters of observational objects. The tasks to be solved are: to formalize the procedure of statistical image segmentation in conditions of incomplete a priori information about objects classes and unknown distribution densities of classification characteristics; to build effective algorithms for detection and linking contour points; to choose a universal mathematical model for describing the geometric shape of both the object and its structural components and to develop a robust method for estimating the model parameters. The methods used are: statistical methods of pattern recognition, methods of probability theory and mathematical statistics, methods of contour analysis, numerical methods for conditional optimization. The following results were obtained. The method of multicomponent model synthesis for describing colour, geometric and structural attributes of object images on multichannel images is proposed. In the model terms, the object is represented by a hierarchical set of nested contours, for the selection of which information about the colour characteristics of statistically homogeneous regions of the image is used. Methods for detecting and linking contour points have been developed, which make it possible to obtain the coordinates of the boundaries circular sweep for both convex and concave geometric objects. As a universal basis for describing the model components, the Johnson SB distribution is adopted, which allows us to describe practically any unimodal and wide class of bimodal distributions. A method for Johnson distribution parameters’ estimation from sample data, based on the method of moments and using optimization procedures for a non-linear objective function with constraints is given. Conclusions. The scientific novelty of the results obtained is as follows: the methods for describing the objects’ images in the form of a combination of several bright-geometric elements and structural connections between them have been further developed, which makes it possible to comprehensively take into account the attribute features of objects in the procedures for analyzing and interpreting images, automatically detecting and locating objects with specified characteristics
14
Sun, Chengyuan, Yihang Du, Xiaoqiang Qiao, Hao Wu, and Tao Zhang. "Research on the Enhancement Method of Specific Emitter Open Set Recognition." Electronics 12, no. 21 (October 24, 2023): 4399. http://dx.doi.org/10.3390/electronics12214399.
Full textAbstract:
Open set recognition (OSR) aims at dealing with unknown classes that are not included in the train set. However, existing OSR methods rely on deep learning networks that perform supervised learning on known classes in the train set, resulting in poor performance when the unknown class is very similar to the known class. Considering the subtle individual differences under the same type in specific emitter identification (SEI) applications, it is difficult to distinguish between known classes and unknown classes in open set scenarios. This paper proposes a pseudo signal generation and recognition neural network (PSGRNN) to address relevant problems in this situation. PSGRNN applies complex-value convolution operations to accommodate IQ signal inputs. Its key idea is to utilize samples of known classes to generate pseudo samples of unknown classes. Then, the samples of known classes and the generated pseudo samples of unknown classes are jointly input into the neural network to construct a new classification task for training. Moreover, the center loss is improved by adding inter-class penalties to maximize the inter-class difference. This helps to learn useful information for separating known and unknown classes, resulting in clearer decision boundaries between the known and the unknown. Extensive experiments on various benchmark signal datasets indicate that the proposed method achieves more accurate and robust open set classification results, with an average accuracy improvement of 4.62%.
15
Li, Xiaolin, Binbin Chen, Jianxiang Li, Shuwu Chen, and Shiguo Huang. "Cosine Distance Loss for Open-Set Image Recognition." Electronics 14, no. 1 (January 4, 2025): 180. https://doi.org/10.3390/electronics14010180.
Full textAbstract:
Traditional image classification often misclassifies unknown samples as known classes during testing, degrading recognition accuracy. Open-set image recognition can simultaneously detect known classes (KCs) and unknown classes (UCs) but still struggles to improve recognition performance caused by open space risk. Therefore, we introduce a cosine distance loss function (CDLoss), which exploits the orthogonality of one-hot encoding vectors to align known samples with their corresponding one-hot encoder directions. This reduces the overlap between the feature spaces of KCs and UCs, mitigating open space risk. CDLoss was incorporated into both Softmax-based and prototype-learning-based frameworks to evaluate its effectiveness. Experimental results show that CDLoss improves AUROC, OSCR, and accuracy across both frameworks and different datasets. Furthermore, various weight combinations of the ARPL and CDLoss were explored, revealing optimal performance with a 1:2 ratio. T-SNE analysis confirms that CDLoss reduces the overlap between the feature spaces of KCs and UCs. These results demonstrate that CDLoss helps mitigate open space risk, enhancing recognition performance in open-set image classification tasks.
16
Liu, Lijun, Rui Wang, Yuan Wang, Lihua Jing, and Chuan Wang. "Frequency Shuffling and Enhancement for Open Set Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 4 (March 24, 2024): 3675–83. http://dx.doi.org/10.1609/aaai.v38i4.28157.
Full textAbstract:
Open-Set Recognition (OSR) aims to accurately identify known classes while effectively rejecting unknown classes to guarantee reliability. Most existing OSR methods focus on learning in the spatial domain, where subtle texture and global structure are potentially intertwined. Empirical studies have shown that DNNs trained in the original spatial domain are inclined to over-perceive subtle texture. The biased semantic perception could lead to catastrophic over-confidence when predicting both known and unknown classes. To this end, we propose an innovative approach by decomposing the spatial domain to the frequency domain to separately consider global (low-frequency) and subtle (high-frequency) information, named Frequency Shuffling and Enhancement (FreSH). To alleviate the overfitting of subtle texture, we introduce the High-Frequency Shuffling (HFS) strategy that generates diverse high-frequency information and promotes the capture of low-frequency invariance. Moreover, to enhance the perception of global structure, we propose the Low-Frequency Residual (LFR) learning procedure that constructs a composite feature space, integrating low-frequency and original spatial features. Experiments on various benchmarks demonstrate that the proposed FreSH consistently trumps the state-of-the-arts by a considerable margin.
17
Wu, Mingrui, Yuqi Liu, Jiayi Ji, Xiaoshuai Sun, and Rongrong Ji. "Toward Open-Set Human Object Interaction Detection." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (March 24, 2024): 6066–73. http://dx.doi.org/10.1609/aaai.v38i6.28422.
Full textAbstract:
This work is oriented toward the task of open-set Human Object Interaction (HOI) detection. The challenge lies in identifying completely new, out-of-domain relationships, as opposed to in-domain ones which have seen improvements in zero-shot HOI detection. To address this challenge, we introduce a simple Disentangled HOI Detection (DHD) model for detecting novel relationships by integrating an open-set object detector with a Visual Language Model (VLM). We utilize a disentangled image-text contrastive learning metric for training and connect the bottom-up visual features to text embeddings through lightweight unary and pair-wise adapters. Our model can benefit from the open-set object detector and the VLM to detect novel action categories and combine actions with novel object categories. We further present the VG-HOI dataset, a comprehensive benchmark with over 17k HOI relationships for open-set scenarios. Experimental results show that our model can detect unknown action classes and combine unknown object classes. Furthermore, it can generalize to over 17k HOI classes while being trained on just 600 HOI classes.
18
Hu, Xinyi, Chunxiang Gu, Yihang Chen, Xi Chen, and Fushan Wei. "OpenCBD: A Network-Encrypted Unknown Traffic Identification Scheme Based on Open-Set Recognition." Wireless Communications and Mobile Computing 2022 (May 12, 2022): 1–18. http://dx.doi.org/10.1155/2022/1746373.
Full textAbstract:
The encryption of network traffic promotes the development of encrypted traffic classification and identification research. However, many existing studies are only effective for closed-set experimental data, that is to say, only for traffic of known classes, while there are often lots of unknown classes traffic in the real environment of open sets, and many studies have difficulty identifying the traffic of unknown classes and can only misclassify them as known classes. How to identify unknown traffic and classify known traffic in an open-collection environment is one of the focuses of traffic analysis research. Considering these problems, this paper proposes a novel solution, which applies the open-set recognition method to the unknown traffic identification, and constructs a model based on deep learning and ensemble learning. The method constructs a model based on a convolutional neural network and a transformer encoder and then uses a three-stage training and testing process, combined with a novel loss function, to generalize to the open space to form OpenCBD. Experiments on public datasets show that the proposed method is significantly better than other open-set identification methods. It can not only distinguish known traffic from unknown traffic but also identify specific classes of known traffic.
19
Chen, Xiangwei, Zhijin Zhao, Xueyi Ye, Shilian Zheng, Caiyi Lou, and Xiaoniu Yang. "Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning." Applied Sciences 12, no. 9 (April 26, 2022): 4380. http://dx.doi.org/10.3390/app12094380.
Full textAbstract:
Interference classification plays an important role in anti-jamming communication. Although the existing interference signal recognition methods based on deep learning have a higher accuracy than traditional methods, these have poor robustness while rejecting interference signals of unknown classes in interference open-set recognition (OSR). To ensure the classification accuracy of the known classes and the rejection rate of the unknown classes in interference OSR, we propose a new hollow convolution prototype learning (HCPL) in which the inner-dot-based cross-entropy loss (ICE) and the center loss are used to update prototypes to the periphery of the feature space so that the internal space is left for the unknown class samples, and the radius loss is used to reduce the impact of the prototype norm on the rejection rate of unknown classes. Then, a hybrid attention and feature reuse net (HAFRNet) for interference signal classification was designed, which contains a feature reuse structure and hybrid domain attention module (HDAM). A feature reuse structure is a simple DenseNet structure without a transition layer. An HDAM can recalibrate both time-wise and channel-wise feature responses by constructing a global attention matrix automatically. We also carried out simulation experiments on nine interference types, which include single-tone jamming, multitone jamming, periodic Gaussian pulse jamming, frequency hopping jamming, linear sweeping frequency jamming, second sweeping frequency jamming, BPSK modulation jamming, noise frequency modulation jamming and QPSK modulation jamming. The simulation results show that the proposed method has considerable classification accuracy of the known classes and rejection performance of the unknown classes. When the JNR is −10 dB, the classification accuracy of the known classes of the proposed method is 2–7% higher than other algorithms under different openness. When the openness is 0.030, the unknown class rejection performance plateau of the proposed method reaches 0.9883, while GCPL is 0.9403 and CG-Encoder is 0.9869; when the openness is 0.397, the proposed method is more than 0.89, while GCPL is 0.8102 and CG-Encoder is 0.9088. However, the rejection performance of unknown classes of CG-Encoder is much worse than that of the proposed method under low JNR. In addition, the proposed method requires less storage resources and has a lower computational complexity than CG-Encoder.
20
Chen, Xiangwei, Zhijin Zhao, Xueyi Ye, Shilian Zheng, Caiyi Lou, and Xiaoniu Yang. "Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning." Applied Sciences 12, no. 9 (April 26, 2022): 4380. http://dx.doi.org/10.3390/app12094380.
Full textAbstract:
Interference classification plays an important role in anti-jamming communication. Although the existing interference signal recognition methods based on deep learning have a higher accuracy than traditional methods, these have poor robustness while rejecting interference signals of unknown classes in interference open-set recognition (OSR). To ensure the classification accuracy of the known classes and the rejection rate of the unknown classes in interference OSR, we propose a new hollow convolution prototype learning (HCPL) in which the inner-dot-based cross-entropy loss (ICE) and the center loss are used to update prototypes to the periphery of the feature space so that the internal space is left for the unknown class samples, and the radius loss is used to reduce the impact of the prototype norm on the rejection rate of unknown classes. Then, a hybrid attention and feature reuse net (HAFRNet) for interference signal classification was designed, which contains a feature reuse structure and hybrid domain attention module (HDAM). A feature reuse structure is a simple DenseNet structure without a transition layer. An HDAM can recalibrate both time-wise and channel-wise feature responses by constructing a global attention matrix automatically. We also carried out simulation experiments on nine interference types, which include single-tone jamming, multitone jamming, periodic Gaussian pulse jamming, frequency hopping jamming, linear sweeping frequency jamming, second sweeping frequency jamming, BPSK modulation jamming, noise frequency modulation jamming and QPSK modulation jamming. The simulation results show that the proposed method has considerable classification accuracy of the known classes and rejection performance of the unknown classes. When the JNR is −10 dB, the classification accuracy of the known classes of the proposed method is 2–7% higher than other algorithms under different openness. When the openness is 0.030, the unknown class rejection performance plateau of the proposed method reaches 0.9883, while GCPL is 0.9403 and CG-Encoder is 0.9869; when the openness is 0.397, the proposed method is more than 0.89, while GCPL is 0.8102 and CG-Encoder is 0.9088. However, the rejection performance of unknown classes of CG-Encoder is much worse than that of the proposed method under low JNR. In addition, the proposed method requires less storage resources and has a lower computational complexity than CG-Encoder.
21
Cao, Alexander, Yuan Luo, and Diego Klabjan. "Open-Set Recognition with Gaussian Mixture Variational Autoencoders." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (May 18, 2021): 6877–84. http://dx.doi.org/10.1609/aaai.v35i8.16848.
Full textAbstract:
In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train explicit closed-set classifiers, in some cases disjointly utilizing reconstruction, which we find dilutes the latent representation's ability to distinguish unknown classes. In contrast, we train our model to cooperatively learn reconstruction and perform class-based clustering in the latent space. With this, our Gaussian mixture variational autoencoder (GMVAE) achieves more accurate and robust open-set classification results, with an average F1 increase of 0.26, through extensive experiments aided by analytical results.
22
Zhang, Yong, Jie Niu, Da Guo, Yinglei Teng, and Xuyan Bao. "Unknown Network Attack Detection Based on Open Set Recognition." Procedia Computer Science 174 (2020): 387–92. http://dx.doi.org/10.1016/j.procs.2020.06.104.
Full text
23
Gao, Fei, Xin Luo, Rongling Lang, Jun Wang, Jinping Sun, and Amir Hussain. "Exploring Reinforced Class Separability and Discriminative Representations for SAR Target Open Set Recognition." Remote Sensing 16, no. 17 (September 3, 2024): 3277. http://dx.doi.org/10.3390/rs16173277.
Full textAbstract:
Current synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms primarily operate under the closed-set assumption, implying that all target classes have been previously learned during the training phase. However, in open scenarios, they may encounter target classes absent from the training set, thereby necessitating an open set recognition (OSR) challenge for SAR-ATR. The crux of OSR lies in establishing distinct decision boundaries between known and unknown classes to mitigate confusion among different classes. To address this issue, we introduce a novel framework termed reinforced class separability for SAR target open set recognition (RCS-OSR), which focuses on optimizing prototype distribution and enhancing the discriminability of features. First, to capture discriminative features, a cross-modal causal features enhancement module (CMCFE) is proposed to strengthen the expression of causal regions. Subsequently, regularized intra-class compactness loss (RIC-Loss) and intra-class relationship aware consistency loss (IRC-Loss) are devised to optimize the embedding space. In conjunction with joint supervised training using cross-entropy loss, RCS-OSR can effectively reduce empirical classification risk and open space risk simultaneously. Moreover, a class-aware OSR classifier with adaptive thresholding is designed to leverage the differences between different classes. Consequently, our method can construct distinct decision boundaries between known and unknown classes to simultaneously classify known classes and identify unknown classes in open scenarios. Extensive experiments conducted on the MSTAR dataset demonstrate the effectiveness and superiority of our method in various OSR tasks.
24
Zhang, Xuelin, Xuelian Cheng, Donghao Zhang, Paul Bonnington, and Zongyuan Ge. "Learning Network Architecture for Open-Set Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 3 (June 28, 2022): 3362–70. http://dx.doi.org/10.1609/aaai.v36i3.20246.
Full textAbstract:
Given the incomplete knowledge of classes that exist in the world, Open-set Recognition (OSR) enables networks to identify and reject the unseen classes after training. This problem of breaking the common closed-set assumption is far from being solved. Recent studies focus on designing new losses, neural network encoding structures, and calibration methods to optimize a feature space for OSR relevant tasks. In this work, we make the first attempt to tackle OSR by searching the architecture of a Neural Network (NN) under the open-set assumption. In contrast to the prior arts, we develop a mechanism to both search the architecture of the network and train a network suitable for tackling OSR. Inspired by the compact abating probability (CAP) model, which is theoretically proven to reduce the open space risk, we regularize the searching space by VAE contrastive learning. To discover a more robust structure for OSR, we propose Pseudo Auxiliary Searching (PAS), in which we split a pretended set of know-unknown classes from the original training set in the searching phase, hence enabling the super-net to explore an effective architecture that can handle unseen classes in advance. We demonstrate the benefits of this learning pipeline on 5 OSR datasets, including MNIST, SVHN, CIFAR10, CIFARAdd10, and CIFARAdd50, where our approach outperforms prior state-of-the-art networks designed by humans. To spark research in this field, our code is available at https://github.com/zxl101/NAS OSR.
25
Jiang, Chunyun, Huiqiang Zhang, Ronghui Zhan, Wenyu Shu, and Jun Zhang. "Open-Set Recognition Model for SAR Target Based on Capsule Network with the KLD." Remote Sensing 16, no. 17 (August 26, 2024): 3141. http://dx.doi.org/10.3390/rs16173141.
Full textAbstract:
Synthetic aperture radar (SAR) automatic target recognition (ATR) technology has seen significant advancements. Despite these advancements, the majority of research still operates under the closed-set assumption, wherein all test samples belong to classes seen during the training phase. In real-world applications, however, it is common to encounter targets not previously seen during training, posing a significant challenge to the existing methods. Ideally, an ATR system should not only accurately identify known target classes but also effectively reject those belonging to unknown classes, giving rise to the concept of open set recognition (OSR). To address this challenge, we propose a novel approach that leverages the unique capabilities of the Capsule Network and the Kullback-Leibler divergence (KLD) to distinguish unknown classes. This method begins by deeply mining the features of SAR targets using the Capsule Network and enhancing the separability between different features through a specially designed loss function. Subsequently, the KLD of features between a testing sample and the center of each known class is calculated. If the testing sample exhibits a significantly larger KLD compared to all known classes, it is classified as an unknown target. The experimental results of the SAR-ACD dataset demonstrate that our method can maintain a correct identification rate of over 95% for known classes while effectively recognizing unknown classes. Compared to existing techniques, our method exhibits significant improvements.
26
Kim, Seongyeop, Hyung-Il Kim, and Yong Man Ro. "Improving Open Set Recognition via Visual Prompts Distilled from Common-Sense Knowledge." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (March 24, 2024): 2786–94. http://dx.doi.org/10.1609/aaai.v38i3.28058.
Full textAbstract:
Open Set Recognition (OSR) poses significant challenges in distinguishing known from unknown classes. In OSR, the overconfidence problem has become a persistent obstacle, where visual recognition models often misclassify unknown objects as known objects with high confidence. This issue stems from the fact that visual recognition models often lack the integration of common-sense knowledge, a feature that is naturally present in language-based models but lacking in visual recognition systems. In this paper, we propose a novel approach to enhance OSR performance by distilling common-sense knowledge into visual prompts. Utilizing text prompts that embody common-sense knowledge about known classes, the proposed visual prompt is learned by extracting semantic common-sense features and aligning them with image features from visual recognition models. The unique aspect of this work is the training of individual visual prompts for each class to encapsulate this common-sense knowledge. Our methodology is model-agnostic, capable of enhancing OSR across various visual recognition models, and computationally light as it focuses solely on training the visual prompts. This research introduces a method for addressing OSR, aiming at a more systematic integration of visual recognition systems with common-sense knowledge. The obtained results indicate an enhancement in recognition accuracy, suggesting the applicability of this approach in practical settings.
27
Morgan, Mallory M., and Jonas Braasch. "Open set classification strategies for long-term environmental field recordings for bird species recognition." Journal of the Acoustical Society of America 151, no. 6 (June 2022): 4028–38. http://dx.doi.org/10.1121/10.0011466.
Full textAbstract:
Deep learning is one established tool for carrying out classification tasks on complex, multi-dimensional data. Since audio recordings contain a frequency and temporal component, long-term monitoring of bioacoustics recordings is made more feasible with these computational frameworks. Unfortunately, these neural networks are rarely designed for the task of open set classification in which examples belonging to the training classes must not only be correctly classified but also crucially separated from any spurious or unknown classes. To combat this reliance on closed set classifiers which are singularly inappropriate for monitoring applications in which many non-relevant sounds are likely to be encountered, the performance of several open set classification frameworks is compared on environmental audio datasets recorded and published within this work, containing both biological and anthropogenic sounds. The inference-based open set classification techniques include prediction score thresholding, distance-based thresholding, and OpenMax. Each open set classification technique is evaluated under multi-, single-, and cross-corpus scenarios for two different types of unknown data, configured to highlight common challenges inherent to real-world classification tasks. The performance of each method is highly dependent upon the degree of similarity between the training, testing, and unknown domain.
28
Tang, Yan, Zhijin Zhao, Chun Li, and Xueyi Ye. "Open set recognition algorithm based on Conditional Gaussian Encoder." Mathematical Biosciences and Engineering 18, no. 5 (2021): 6620–37. http://dx.doi.org/10.3934/mbe.2021328.
Full textAbstract:
<abstract> <p>For the existing Closed Set Recognition (CSR) methods mistakenly identify unknown jamming signals as a known class, a Conditional Gaussian Encoder (CG-Encoder) for 1-dimensional signal Open Set Recognition (OSR) is designed. The network retains the original form of the signal as much as possible and deep neural network is used to extract useful information. CG-Encoder adopts residual network structure and a new Kullback-Leibler (KL) divergence is defined. In the training phase, the known classes are approximated to different Gaussian distributions in the latent space and the discrimination between classes is increased to improve the recognition performance of the known classes. In the testing phase, a specific and effective OSR algorithm flow is designed. Simulation experiments are carried out on 9 jamming types. The results show that the CSR and OSR performance of CG-Encoder is better than that of the other three kinds of network structures. When the openness is the maximum, the open set average accuracy of CG-Encoder is more than 70%, which is about 30% higher than the worst algorithm, and about 20% higher than the better one. When the openness is the minimum, the average accuracy of OSR is more than 95%.</p> </abstract>
29
Zhang, Wei, Da Huang, Minghui Zhou, Jingran Lin, and Xiangfeng Wang. "Open-Set Signal Recognition Based on Transformer and Wasserstein Distance." Applied Sciences 13, no. 4 (February 7, 2023): 2151. http://dx.doi.org/10.3390/app13042151.
Full textAbstract:
Open-set signal recognition provides a new approach for verifying the robustness of models by introducing novel unknown signal classes into the model testing and breaking the conventional closed-set assumption, which has become very popular in real-world scenarios. In the present work, we propose an efficient open-set signal recognition algorithm, which contains three key sub-modules: the signal representation sub-module based on a vision transformer (ViT) structure, a set distance metric sub-module based on Wasserstein distance, and a class space compression sub-module based on reciprocal point separation and central loss. In this algorithm, the representing features of signals are established based on transformer-based neural networks, i.e., ViT, in order to extract global information about time series-related data. The employed reciprocal point is used in modeling the potential unknown space without using the corresponding samples, while the distance metric between different class spaces is mathematically modeled in terms of the Wasserstein distance instead of the classical Euclidean distance. Numerical experiments on different open-set signal recognition tasks show that the proposed algorithm can significantly improve the recognition efficiency in both known and unknown categories.
30
Pires, Catarina, Marília Barandas, Letícia Fernandes, Duarte Folgado, and Hugo Gamboa. "Towards Knowledge Uncertainty Estimation for Open Set Recognition." Machine Learning and Knowledge Extraction 2, no. 4 (October 30, 2020): 505–32. http://dx.doi.org/10.3390/make2040028.
Full textAbstract:
Uncertainty is ubiquitous and happens in every single prediction of Machine Learning models. The ability to estimate and quantify the uncertainty of individual predictions is arguably relevant, all the more in safety-critical applications. Real-world recognition poses multiple challenges since a model’s knowledge about physical phenomenon is not complete, and observations are incomplete by definition. However, Machine Learning algorithms often assume that train and test data distributions are the same and that all testing classes are present during training. A more realistic scenario is the Open Set Recognition, where unknown classes can be submitted to an algorithm during testing. In this paper, we propose a Knowledge Uncertainty Estimation (KUE) method to quantify knowledge uncertainty and reject out-of-distribution inputs. Additionally, we quantify and distinguish aleatoric and epistemic uncertainty with the classical information-theoretical measures of entropy by means of ensemble techniques. We performed experiments on four datasets with different data modalities and compared our results with distance-based classifiers, SVM-based approaches and ensemble techniques using entropy measures. Overall, the effectiveness of KUE in distinguishing in- and out-distribution inputs obtained better results in most cases and was at least comparable in others. Furthermore, a classification with rejection option based on a proposed combination strategy between different measures of uncertainty is an application of uncertainty with proven results.
31
Li, Xue, Jinlong Fei, Jiangtao Xie, Ding Li, Heng Jiang, Ruonan Wang, and Zan Qi. "Open Set Recognition for Malware Traffic via Predictive Uncertainty." Electronics 12, no. 2 (January 8, 2023): 323. http://dx.doi.org/10.3390/electronics12020323.
Full textAbstract:
Existing machine learning-based malware traffic recognition techniques can effectively detect abnormal behaviors in the network. However, almost all of them focus on a closed-set scenario in which the data used for training and testing come from the same label space. Since sophisticated malware and advanced persistent threats are evolving, it is impossible to exhaust all attacks to train a complete recognition model under the existing technical conditions. Therefore, recognition in the real network is an open-set problem, i.e., the recognition system should identify unknown and unseen attacks at test time. In this paper, we propose an uncertainty-aware method to identify known malicious traffic accurately and handle unknown traffic effectively. This method employs predictive uncertainty in deep learning as an indicator for unknown class detection. The predictive uncertainty represents the confidence in neural network predictions. In particular, the Deep Evidence Malware Traffic Recognition (DEMTR) model is presented to provide the multi-classification probability and predictive uncertainty in open-set scenarios using evidential deep learning. We demonstrate the performance of DEMTR on the MCFP dataset. Experimental results indicate that the proposed model outperforms the baseline methods in accuracy and F1-score.
32
Wang, Chao, Bailing Wang, Yunxiao Sun, Yuliang Wei, Kai Wang, Hui Zhang, and Hongri Liu. "Intrusion Detection for Industrial Control Systems Based on Open Set Artificial Neural Network." Security and Communication Networks 2021 (August 18, 2021): 1–14. http://dx.doi.org/10.1155/2021/4027900.
Full textAbstract:
The security of industrial control systems (ICSs) has received a lot of attention in recent years. ICSs were once closed networks. But with the development of IT technologies, ICSs have become connected to the Internet, increasing the potential of cyberattacks. Because ICSs are so tightly linked to human lives, any harm to them could have disastrous implications. As a technique of providing protection, many intrusion detection system (IDS) studies have been conducted. However, because of the complicated network environment and rising means of attack, it is difficult to cover all attack classes, most of the existing classification techniques are hard to deploy in a real environment since they cannot deal with the open set problem. We propose a novel artificial neural network based-methodology to solve this problem. Our suggested method can classify known classes while also detecting unknown classes. We conduct research from two points of view. On the one hand, we use the openmax layer instead of the traditional softmax layer. Openmax overcomes the limitations of softmax, allowing neural networks to detect unknown attack classes. During training, on the other hand, a new loss function termed center loss is implemented to improve detection ability. The neural network model learns better feature representations with the combined supervision of center loss and softmax loss. We evaluate the neural network on NF-BoT-IoT-v2 and Gas Pipeline datasets. The experiments show our proposed method is comparable with the state-of-the-art algorithm in terms of detecting unknown classes. But our method has a better overall classification performance.
33
Boult, T. E., S. Cruz, A. R. Dhamija, M. Gunther, J. Henrydoss, and W. J. Scheirer. "Learning and the Unknown: Surveying Steps toward Open World Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9801–7. http://dx.doi.org/10.1609/aaai.v33i01.33019801.
Full textAbstract:
As science attempts to close the gap between man and machine by building systems capable of learning, we must embrace the importance of the unknown. The ability to differentiate between known and unknown can be considered a critical element of any intelligent self-learning system. The ability to reject uncertain inputs has a very long history in machine learning, as does including a background or garbage class to account for inputs that are not of interest. This paper explains why neither of these is genuinely sufficient for handling unknown inputs – uncertain is not unknown, and unknowns need not appear to be uncertain to a learning system. The past decade has seen the formalization and development of many open set algorithms, which provably bound the risk from unknown classes. We summarize the state of the art, core ideas, and results and explain why, despite the efforts to date, the current techniques are genuinely insufficient for handling unknown inputs, especially for deep networks.
34
Wang, Huaqing, Zhitao Xu, Xingwei Tong, and Liuyang Song. "Cross-Domain Open Set Fault Diagnosis Based on Weighted Domain Adaptation with Double Classifiers." Sensors 23, no. 4 (February 14, 2023): 2137. http://dx.doi.org/10.3390/s23042137.
Full textAbstract:
The application of transfer learning in fault diagnosis has been developed in recent years. It can use existing data to solve the problem of fault recognition under different working conditions. Due to the complexity of the equipment and the openness of the working environment in industrial production, the status of the equipment is changeable, and the collected signals can have new fault classes. Therefore, the open set recognition ability of the transfer learning method is an urgent research direction. The existing transfer learning model can have a severe negative transfer problem when solving the open set problem, resulting in the aliasing of samples in the feature space and the inability to separate the unknown classes. To solve this problem, we propose a Weighted Domain Adaptation with Double Classifiers (WDADC) method. Specifically, WDADC designs the weighting module based on Jensen–Shannon divergence, which can evaluate the similarity between each sample in the target domain and each class in the source domain. Based on this similarity, a weighted loss is constructed to promote the positive transfer between shared classes in the two domains to realize the recognition of shared classes and the separation of unknown classes. In addition, the structure of double classifiers in WDADC can mitigate the overfitting of the model by maximizing the discrepancy, which helps extract the domain-invariant and class-separable features of the samples when the discrepancy between the two domains is large. The model’s performance is verified in several fault datasets of rotating machinery. The results show that the method is effective in open set fault diagnosis and superior to the common domain adaptation methods.
35
Giusti, Elisa, Selenia Ghio, Amir Hosein Oveis, and Marco Martorella. "Proportional Similarity-Based Openmax Classifier for Open Set Recognition in SAR Images." Remote Sensing 14, no. 18 (September 19, 2022): 4665. http://dx.doi.org/10.3390/rs14184665.
Full textAbstract:
Most of the existing Non-Cooperative Target Recognition (NCTR) systems follow the “closed world” assumption, i.e., they only work with what was previously observed. Nevertheless, the real world is relatively “open” in the sense that the knowledge of the environment is incomplete. Therefore, unknown targets can feed the recognition system at any time while it is operational. Addressing this issue, the Openmax classifier has been recently proposed in the optical domain to make convolutional neural networks (CNN) able to reject unknown targets. There are some fundamental limitations in the Openmax classifier that can end up with two potential errors: (1) rejecting a known target and (2) classifying an unknown target. In this paper, we propose a new classifier to increase the robustness and accuracy. The proposed classifier, which is inspired by the limitations of the Openmax classifier, is based on proportional similarity between the test image and different training classes. We evaluate our method by radar images of man-made targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. Moreover, a more in-depth discussion on the Openmax hyper-parameters and a detailed description of the Openmax functioning are given.
36
Naranjo-Alcazar, Javier, Sergi Perez-Castanos, Pedro Zuccarello, Fabio Antonacci, and Maximo Cobos. "Open Set Audio Classification Using Autoencoders Trained on Few Data." Sensors 20, no. 13 (July 3, 2020): 3741. http://dx.doi.org/10.3390/s20133741.
Full textAbstract:
Open-set recognition (OSR) is a challenging machine learning problem that appears when classifiers are faced with test instances from classes not seen during training. It can be summarized as the problem of correctly identifying instances from a known class (seen during training) while rejecting any unknown or unwanted samples (those belonging to unseen classes). Another problem arising in practical scenarios is few-shot learning (FSL), which appears when there is no availability of a large number of positive samples for training a recognition system. Taking these two limitations into account, a new dataset for OSR and FSL for audio data was recently released to promote research on solutions aimed at addressing both limitations. This paper proposes an audio OSR/FSL system divided into three steps: a high-level audio representation, feature embedding using two different autoencoder architectures and a multi-layer perceptron (MLP) trained on latent space representations to detect known classes and reject unwanted ones. An extensive set of experiments is carried out considering multiple combinations of openness factors (OSR condition) and number of shots (FSL condition), showing the validity of the proposed approach and confirming superior performance with respect to a baseline system based on transfer learning.
37
Zhang, Bo, Feixuan Li, Ning Ma, Wen Ji, and See-Kiong Ng. "Open Set Bearing Fault Diagnosis with Domain Adaptive Adversarial Network under Varying Conditions." Actuators 13, no. 4 (March 25, 2024): 121. http://dx.doi.org/10.3390/act13040121.
Full textAbstract:
Bearing fault diagnosis is a pivotal aspect of monitoring rotating machinery. Recently, numerous deep learning models have been developed for intelligent bearing fault diagnosis. However, these models have typically been established based on two key assumptions: (1) that identical fault categories exist in both the training and testing datasets, and (2) the datasets used for testing and training are assumed to follow the same distribution. Nevertheless, these assumptions prove impractical and fail to accurately depict real-world scenarios, particularly those involving open-world assumption fault diagnosis in multi-condition scenarios. For that purpose, an open set domain adaptive adversarial network framework is proposed. Specifically, in order to improve the learning of distribution characteristics in different fields, comprehensive training is implemented using a deep convolutional autoencoder model. Additionally, to mitigate the negative transfer resulting from unknown fault samples in the target domain, the similarity of each target domain sample and the shared classes in the source domain are estimated using known class classifiers and extended classifiers. Similarity weight values are assigned to each target domain sample, and an unknown boundary is established in a weighted manner. This approach is employed to establish the alignment between the classes shared between the two domains, enabling the classification of known fault classes, while allowing the recognition of unknown fault classes in the target domain. The efficacy of our suggested approach is empirically validated using different datasets.
38
Chen, Minwei, Yajun Liu, Zenghui Zhang, and Weiwei Guo. "RCRFNet: Enhancing Object Detection with Self-Supervised Radar–Camera Fusion and Open-Set Recognition." Sensors 24, no. 15 (July 24, 2024): 4803. http://dx.doi.org/10.3390/s24154803.
Full textAbstract:
Robust object detection in complex environments, poor visual conditions, and open scenarios presents significant technical challenges in autonomous driving. These challenges necessitate the development of advanced fusion methods for millimeter-wave (mmWave) radar point cloud data and visual images. To address these issues, this paper proposes a radar–camera robust fusion network (RCRFNet), which leverages self-supervised learning and open-set recognition to effectively utilise the complementary information from both sensors. Specifically, the network uses matched radar–camera data through a frustum association approach to generate self-supervised signals, enhancing network training. The integration of global and local depth consistencies between radar point clouds and visual images, along with image features, helps construct object class confidence levels for detecting unknown targets. Additionally, these techniques are combined with a multi-layer feature extraction backbone and a multimodal feature detection head to achieve robust object detection. Experiments on the nuScenes public dataset demonstrate that RCRFNet outperforms state-of-the-art (SOTA) methods, particularly in conditions of low visual visibility and when detecting unknown class objects.
39
Adayel, Reham, Yakoub Bazi, Haikel Alhichri, and Naif Alajlan. "Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking." Remote Sensing 12, no. 11 (May 27, 2020): 1716. http://dx.doi.org/10.3390/rs12111716.
Full textAbstract:
Most of the existing domain adaptation (DA) methods proposed in the context of remote sensing imagery assume the presence of the same land-cover classes in the source and target domains. Yet, this assumption is not always realistic in practice as the target domain may contain additional classes unknown to the source leading to the so-called open set DA. Under this challenging setting, the problem turns to reducing the distribution discrepancy between the shared classes in both domains besides the detection of the unknown class samples in the target domain. To deal with the openset problem, we propose an approach based on adversarial learning and pareto-based ranking. In particular, the method leverages the distribution discrepancy between the source and target domains using min-max entropy optimization. During the alignment process, it identifies candidate samples of the unknown class from the target domain through a pareto-based ranking scheme that uses ambiguity criteria based on entropy and the distance to source class prototype. Promising results using two cross-domain datasets that consist of very high resolution and extremely high resolution images, show the effectiveness of the proposed method.
40
Xu, Tuo, Ying Wang, Jie Li, and Yuefan Du. "Generative Adversarial Network and Mutual-Point Learning Algorithm for Few-Shot Open-Set Classification of Hyperspectral Images." Remote Sensing 16, no. 7 (April 5, 2024): 1285. http://dx.doi.org/10.3390/rs16071285.
Full textAbstract:
Existing approaches addressing the few-shot open-set recognition (FSOSR) challenge in hyperspectral images (HSIs) often encounter limitations stemming from sparse labels, restricted category numbers, and low openness. These limitations compromise stability and adaptability. In response, an open-set HSI classification algorithm based on data wandering (DW) is introduced in this research. Firstly, a K-class classifier suitable for a closed set is trained, and its internal encoder is leveraged to extract features and estimate the distribution of known categories. Subsequently, the classifier is fine-tuned based on feature distribution. To address the scarcity of samples, a sample density constraint based on the generative adversarial network (GAN) is employed to generate synthetic samples near the decision boundary. Simultaneously, a mutual-point learning method is incorporated to widen the class distance between known and unknown categories. In addition, a dynamic threshold method based on DW is devised to enhance the open-set performance. By categorizing drifting synthetic samples into known and unknown classes and retraining them together with the known samples, the closed-set classifier is optimized, and a (K + 1)-class open-set classifier is trained. The experimental results in this research demonstrate the superior FSOSR performance of the proposed method across three benchmark HSI datasets.
41
Shieh, Chin-Shiuh, Thanh-Tuan Nguyen, Chun-Yueh Chen, and Mong-Fong Horng. "Detection of Unknown DDoS Attack Using Reconstruct Error and One-Class SVM Featuring Stochastic Gradient Descent." Mathematics 11, no. 1 (December 26, 2022): 108. http://dx.doi.org/10.3390/math11010108.
Full textAbstract:
The network system has become an indispensable component of modern infrastructure. DDoS attacks and their variants remain a potential and persistent cybersecurity threat. DDoS attacks block services to legitimate users by incorporating large amounts of malicious traffic in a short period or depleting system resources through methods specific to each client, causing the victim to lose reputation, finances, and potential customers. With the advancement and maturation of artificial intelligence technology, machine learning and deep learning are widely used to detect DDoS attacks with significant success. However, traditional supervised machine learning must depend on the categorized training sets, so the recognition rate plummets when the model encounters patterns outside the dataset. In addition, DDoS attack techniques continue to evolve, rendering training based on conventional data models unable to meet contemporary requirements. Since closed-set classifiers have excellent performance in cybersecurity and are quite mature, this study will investigate the identification of open-set recognition issues where the attack pattern does not accommodate the distribution learned by the model. This research proposes a framework that uses reconstruction error and distributes hidden layer characteristics to detect unknown DDoS attacks. This study will employ deep hierarchical reconstruction nets (DHRNet) architecture and reimplement it with a 1D integrated neural network employing loss function combined with spatial location constraint prototype loss (SLCPL) as a solution for open-set risks. At the output, a one-class SVM (one-class support vector machine) based on a random gradient descent approximation is used to recognize the unknown patterns in the subsequent stage. The model achieves an impressive detection rate of more than 99% in testing. Furthermore, the incremental learning module utilizing unknown traffic labeled by telecom technicians during tracking has enhanced the model’s performance by 99.8% against unknown threats based on the CICIDS2017 Friday open dataset.
42
Di, Chengliang, Jinwei Ji, Chao Sun, and Linlin Liang. "SOAMC: A Semi-Supervised Open-Set Recognition Algorithm for Automatic Modulation Classification." Electronics 13, no. 21 (October 25, 2024): 4196. http://dx.doi.org/10.3390/electronics13214196.
Full textAbstract:
Traditional automatic modulation classification methods operate under the closed-set assumption, which proves to be impractical in real-world scenarios due to the diverse nature of wireless technologies and the dynamic characteristics of wireless propagation environments. Open-set environments introduce substantial technical challenges, particularly in terms of detection effectiveness and computational complexity. To address the limitations of modulation classification and recognition in open-set scenarios, this paper proposes a semi-supervised open-set recognition approach, termed SOAMC (Semi-Supervised Open-Set Automatic Modulation Classification). The primary objective of SOAMC is to accurately classify unknown modulation types, even when only a limited subset of samples is manually labeled. The proposed method consists of three key stages: (1) A signal recognition pre-training model is constructed using data augmentation and adaptive techniques to enhance robustness. (2) Feature extraction and embedding are performed via a specialized extraction network. (3) Label propagation is executed using a graph convolutional neural network (GCN) to efficiently annotate the unlabeled signal samples. Experimental results demonstrate that SOAMC significantly improves classification accuracy, particularly in challenging scenarios with limited amounts of labeled data and high signal similarity. These findings are critical for the practical identification of complex and diverse modulation signals in real-world wireless communication systems.
43
Schmidt, Georg, Stefan Stüring, Norman Richnow, and Ingo Siegert. "Handling of “unknown unknowns” - classification of 3D geometries from CAD open set datasets using Convolutional Neural Networks." Online Journal of Applied Knowledge Management 10, no. 1 (September 6, 2022): 62–76. http://dx.doi.org/10.36965/ojakm.2022.10(1)62-76.
Full textAbstract:
This paper refers to the application of Convolutional Neural Networks (CNNs) for the classification of 3D geometries from Computer-Aided Design (CAD) datasets with a large proportion of unknown unknowns (classes unknown after training). The motivation of the work is the automatic recognition of standard parts in the large CAD-based image data set and thus, reducing the time required for the manual preparation of the data set. The classification is based on a threshold value of the Softmax output layer (first criterion), as well as on three different methods of a second criterion. The three methods for the second criterion are the comparison of metadata relating to the geometries, the comparison of feature vectors from previous dense layers of the CNN with a Spearman correlation, and the distance-based difference between multivariate Gaussian models of these feature vectors using Kullback-Leibler divergence. It is confirmed that all three methods are suitable to solve an open set problem in large 3D datasets (more than 1000 different geometries). Classification and training are image-based using different multi-view representations of the geometries.
44
da Silva, C. C. V., K. Nogueira, H. N. Oliveira, and J. A. dos Santos. "TOWARDS OPEN-SET SEMANTIC SEGMENTATION OF AERIAL IMAGES." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences IV-3/W2-2020 (October 29, 2020): 19–24. http://dx.doi.org/10.5194/isprs-annals-iv-3-w2-2020-19-2020.
Full textAbstract:
Abstract. Classical and more recently deep computer vision methods are optimized for visible spectrum images, commonly encoded in grayscale or RGB colorspaces acquired from smartphones or cameras. A more uncommon source of images exploited in the remote sensing field are satellite and aerial images. However the development of pattern recognition approaches for these data is relatively recent, mainly due to the limited availability of this type of images, as until recently they were used exclusively for military purposes. Access to aerial imagery, including spectral information, has been increasing mainly due to the low cost of drones, cheapening of imaging satellite launch costs, and novel public datasets. Usually remote sensing applications employ computer vision techniques strictly modeled for classification tasks in closed set scenarios. However, real-world tasks rarely fit into closed set contexts, frequently presenting previously unknown classes, characterizing them as open set scenarios. Focusing on this problem, this is the first paper to study and develop semantic segmentation techniques for open set scenarios applied to remote sensing images. The main contributions of this paper are: 1) a discussion of related works in open set semantic segmentation, showing evidence that these techniques can be adapted for open set remote sensing tasks; 2) the development and evaluation of a novel approach for open set semantic segmentation. Our method yielded competitive results when compared to closed set methods for the same dataset.
45
Shin, Jin-Su, Min-Joo Kim, Beom-Seok Kim, and Dong-Hee Lee. "Enhanced detection of unknown defect patterns on wafer bin maps based on an open-set recognition approach." Computers in Industry 164 (January 2025): 104208. http://dx.doi.org/10.1016/j.compind.2024.104208.
Full text
46
Zai El Amri, Wadhah, Felix Reinhart, and Wolfram Schenck. "Open set task augmentation facilitates generalization of deep neural networks trained on small data sets." Neural Computing and Applications 34, no. 8 (December 9, 2021): 6067–83. http://dx.doi.org/10.1007/s00521-021-06753-6.
Full textAbstract:
AbstractMany application scenarios for image recognition require learning of deep networks from small sample sizes in the order of a few hundred samples per class. Then, avoiding overfitting is critical. Common techniques to address overfitting are transfer learning, reduction of model complexity and artificial enrichment of the available data by, e.g., data augmentation. A key idea proposed in this paper is to incorporate additional samples into the training that do not belong to the classes of the target task. This can be accomplished by formulating the original classification task as an open set classification task. While the original closed set classification task is not altered at inference time, the recast as open set classification task enables the inclusion of additional data during training. Hence, the original closed set classification task is augmented with an open set task during training. We therefore call the proposed approach open set task augmentation. In order to integrate additional task-unrelated samples into the training, we employ the entropic open set loss originally proposed for open set classification tasks and also show that similar results can be obtained with a modified sum of squared errors loss function. Learning with the proposed approach benefits from the integration of additional “unknown” samples, which are often available, e.g., from open data sets, and can then be easily integrated into the learning process. We show that this open set task augmentation can improve model performance even when these additional samples are rather few or far from the domain of the target task. The proposed approach is demonstrated on two exemplary scenarios based on subsets of the ImageNet and Food-101 data sets as well as with several network architectures and two loss functions. We further shed light on the impact of the entropic open set loss on the internal representations formed by the networks. Open set task augmentation is particularly valuable when no additional data from the target classes are available—a scenario often faced in practice.
47
Shieh, Chin-Shiuh, Thanh-Tuan Nguyen, and Mong-Fong Horng. "Detection of Unknown DDoS Attack Using Convolutional Neural Networks Featuring Geometrical Metric." Mathematics 11, no. 9 (May 3, 2023): 2145. http://dx.doi.org/10.3390/math11092145.
Full textAbstract:
DDoS attacks remain a persistent cybersecurity threat, blocking services to legitimate users and causing significant damage to reputation, finances, and potential customers. For the detection of DDoS attacks, machine learning techniques such as supervised learning have been extensively employed, but their effectiveness declines when the framework confronts patterns exterior to the dataset. In addition, DDoS attack schemes continue to improve, rendering conventional data model-based training ineffectual. We have developed a novelty open-set recognition framework for DDoS attack detection to overcome the challenges of traditional methods. Our framework is built on a Convolutional Neural Network (CNN) construction featuring geometrical metric (CNN-Geo), which utilizes deep learning techniques to enhance accuracy. In addition, we have integrated an incremental learning module that can efficiently incorporate novel unknown traffic identified by telecommunication experts through the monitoring process. This unique approach provides an effective solution for identifying and alleviating DDoS. The module continuously improves the model’s performance by incorporating new knowledge and adapting to new attack patterns. The proposed model can detect unknown DDoS attacks with a detection rate of over 99% on conventional attacks from CICIDS2017. The model’s accuracy is further enhanced by 99.8% toward unknown attacks with the open datasets CICDDoS2019.
48
Huang, Jing, Bin Wu, Peng Li, Xiao Li, and Jie Wang. "Few-Shot Learning for Radar Emitter Signal Recognition Based on Improved Prototypical Network." Remote Sensing 14, no. 7 (March 31, 2022): 1681. http://dx.doi.org/10.3390/rs14071681.
Full textAbstract:
In recent years, deep learning has been widely used in radar emitter signal identification and has significantly increased recognition rates. However, with the emergence of new institutional radars and an increasingly complex electromagnetic environment, the collection of high-quality signals becomes difficult, leading to a result that the amount of some signal types we own are too few to converge a deep neural network. Moreover, in radar emitter signal identification, most existing networks ignore the signal recognition of unknown classes, which is of vital importance for radar emitter signal identification. To solve these two problems, an improved prototypical network (IPN) belonging to metric-based meta-learning is proposed. Firstly, a reparameterization VGG (RepVGG) net is used to replace the original structure that severely limits the model performance. Secondly, we added a feature adjustment operation to prevent some extreme or unimportant samples from affecting the prototypes. Thirdly, open-set recognition is realized by setting a threshold in the metric module.
49
Chen, Ken, Yulong Duan, Yi Huang, Wei Hu, and Yaoqin Xie. "A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring." Bioengineering 11, no. 1 (December 20, 2023): 2. http://dx.doi.org/10.3390/bioengineering11010002.
Full textAbstract:
Radar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identification from radar sequences is still a challenging task. Furthermore, there is a need to address the open-set recognition problem for radar sequences, which has not been sufficiently studied. In this paper, we propose a deep learning-based approach for human identification using radar sequences captured during sleep in a daily home-monitoring setup. To enhance robustness, we preprocess the sequences to mitigate environmental interference before employing a deep convolution neural network for human identification. We introduce a Principal Component Space feature representation to detect unknown sequences. Our method is rigorously evaluated using both a public data set and a set of experimentally acquired radar sequences. We report a labeling accuracy of 98.2% and 96.8% on average for the two data sets, respectively, which outperforms the state-of-the-art techniques. Our method excels at accurately distinguishing unknown sequences from labeled ones, with nearly 100% detection of unknown samples and minimal misclassification of labeled samples as unknown.
50
Shieh, Chin-Shiuh, Wan-Wei Lin, Thanh-Tuan Nguyen, Chi-Hong Chen, Mong-Fong Horng, and Denis Miu. "Detection of Unknown DDoS Attacks with Deep Learning and Gaussian Mixture Model." Applied Sciences 11, no. 11 (June 4, 2021): 5213. http://dx.doi.org/10.3390/app11115213.
Full textAbstract:
DDoS (Distributed Denial of Service) attacks have become a pressing threat to the security and integrity of computer networks and information systems, which are indispensable infrastructures of modern times. The detection of DDoS attacks is a challenging issue before any mitigation measures can be taken. ML/DL (Machine Learning/Deep Learning) has been applied to the detection of DDoS attacks with satisfactory achievement. However, full-scale success is still beyond reach due to an inherent problem with ML/DL-based systems—the so-called Open Set Recognition (OSR) problem. This is a problem where an ML/DL-based system fails to deal with new instances not drawn from the distribution model of the training data. This problem is particularly profound in detecting DDoS attacks since DDoS attacks’ technology keeps evolving and has changing traffic characteristics. This study investigates the impact of the OSR problem on the detection of DDoS attacks. In response to this problem, we propose a new DDoS detection framework featuring Bi-Directional Long Short-Term Memory (BI-LSTM), a Gaussian Mixture Model (GMM), and incremental learning. Unknown traffic captured by the GMM are subject to discrimination and labeling by traffic engineers, and then fed back to the framework as additional training samples. Using the data sets CIC-IDS2017 and CIC-DDoS2019 for training, testing, and evaluation, experiment results show that the proposed BI-LSTM-GMM can achieve recall, precision, and accuracy up to 94%. Experiments reveal that the proposed framework can be a promising solution to the detection of unknown DDoS attacks.