Littérature scientifique sur le sujet « Unknown classes detection (Open-Set Recognition) »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Unknown classes detection (Open-Set Recognition) ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Articles de revues sur le sujet "Unknown classes detection (Open-Set Recognition)"
1
Xu, Baile, Furao Shen et Jian Zhao. « Contrastive Open Set Recognition ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 9 (26 juin 2023) : 10546–56. http://dx.doi.org/10.1609/aaai.v37i9.26253.
Texte intégralRésumé :
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 et Hongwei Liu. « Radar HRRP Open Set Target Recognition Based on Closed Classification Boundary ». Remote Sensing 15, no 2 (12 janvier 2023) : 468. http://dx.doi.org/10.3390/rs15020468.
Texte intégralRésumé :
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 et Kálmán Tornai. « Improving the Performance of Open-Set Recognition with Generated Fake Data ». Electronics 12, no 6 (9 mars 2023) : 1311. http://dx.doi.org/10.3390/electronics12061311.
Texte intégralRésumé :
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 et Weihong Deng. « Open-Set Facial Expression Recognition ». Proceedings of the AAAI Conference on Artificial Intelligence 38, no 1 (24 mars 2024) : 646–54. http://dx.doi.org/10.1609/aaai.v38i1.27821.
Texte intégralRésumé :
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 et Linrang Zhang. « Intelligent Radar Jamming Recognition in Open Set Environment Based on Deep Learning Networks ». Remote Sensing 14, no 24 (8 décembre 2022) : 6220. http://dx.doi.org/10.3390/rs14246220.
Texte intégralRésumé :
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 et 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 (3 juillet 2023) : 80. http://dx.doi.org/10.3390/mca28040080.
Texte intégralRésumé :
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 et 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 (28 juin 2022) : 131–39. http://dx.doi.org/10.1609/aaai.v36i1.19887.
Texte intégralRésumé :
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, et Joonwhoan Lee. « Open-Set Recognition of Pansori Rhythm Patterns Based on Audio Segmentation ». Applied Sciences 14, no 16 (6 août 2024) : 6893. http://dx.doi.org/10.3390/app14166893.
Texte intégralRésumé :
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 et Shan Lu. « A Novel Method for Unexpected Obstacle Detection in the Traffic Environment Based on Computer Vision ». Applied Sciences 12, no 18 (6 septembre 2022) : 8937. http://dx.doi.org/10.3390/app12188937.
Texte intégralRésumé :
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., et Leon N. Klatt. « Principal Component Analysis of Diffuse Near-Infrared Reflectance Data from Paper Currency ». Applied Spectroscopy 43, no 8 (novembre 1989) : 1399–405. http://dx.doi.org/10.1366/0003702894204470.
Texte intégralRésumé :
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.
Thèses sur le sujet "Unknown classes detection (Open-Set Recognition)"
1
Christoffel, Quentin. « Apprentissage de représentation différenciées dans des modèles d’apprentissage profond : détection de classes inconnues et interprétabilité ». Electronic Thesis or Diss., Strasbourg, 2024. http://www.theses.fr/2024STRAD027.
Texte intégralRésumé :
L’apprentissage profond, et en particulier les réseaux de neurones convolutifs, a révolutionné de nombreux domaines tels que la vision par ordinateur. Cependant, ces modèles restent limités lorsqu’ils rencontrent des données issues de classes inconnues (jamais vues durant l'entraînement) et souffrent souvent d’un manque d’interprétabilité. Nous avons proposé une méthode visant à optimiser directement l’espace de représentation appris par le modèle. Chaque dimension de la représentation est associée à une classe connue. Une dimension doit être activée avec une certaine valeur lorsque le modèle fait face à la classe associée, donc lorsque certaines caractéristiques ont été détectées dans l'image. Cela permet au modèle de détecter les données inconnues par leur représentation distincte des données connues, puisqu'elles ne doivent pas partager les mêmes caractéristiques. Notre approche favorise également des rapprochements sémantiques dans l'espace de représentation en allouant un sous-espace à chaque classe connue. De plus, une certaine interprétabilité est possible en analysant les dimensions activées pour une image donnée, permettant de comprendre quels attributs de quelle classe sont détectés. Cette thèse détaille le développement et l’évaluation de notre méthode à travers plusieurs versions, chacune visant à améliorer les performances et à adresser des limites identifiées grâce à l'interprétabilité, telles que la corrélation des attributs extraits. Les résultats obtenus sur un benchmark de détection de classes inconnues montrent une amélioration notable des performances entre nos différentes versions, bien que présentant des résultats inférieurs à l'état de l'artDeep learning, and particularly convolutional neural networks, has revolutionized numerous fields such as computer vision. However, these models remain limited when encountering data from unknown classes (never seen during training) and often suffer from a lack of interpretability. We proposed a method aimed at directly optimizing the representation space learned by the model. Each dimension of the representation is associated with a known class. A dimension is activated with a specific value when the model faces the associated class, meaning that certain features have been detected in the image. This allows the model to detect unknown data by their distinct representation from known data, as they should not share the same features. Our approach also promotes semantic relationships within the representation space by allocating a subspace to each known class. Moreover, a degree of interpretability is achieved by analysing the activated dimensions for a given image, enabling an understanding of which features of which class are detected. This thesis details the development and evaluation of our method across multiple iterations, each aimed at improving performance and addressing identified limitations through interpretability, such as the correlation of extracted features. The results obtained on an unknown class detection benchmark show a notable improvement in performance between our versions, although they remain below the state-of-the-art
Chapitres de livres sur le sujet "Unknown classes detection (Open-Set Recognition)"
1
Kao, Hao, Thanh-Tuan Nguyen, Chin-Shiuh Shieh, Mong-Fong Horng, Lee Yu Xian et Denis Miu. « Unknown DDoS Attack Detection Using Open-Set Recognition Technology and Fuzzy C-Means Clustering ». Dans Lecture Notes in Electrical Engineering, 366–80. Singapore : Springer Nature Singapore, 2024. http://dx.doi.org/10.1007/978-981-99-9412-0_38.
Texte intégralActes de conférences sur le sujet "Unknown classes detection (Open-Set Recognition)"
1
Brignac, Daniel, et Abhijit Mahalanobis. « Cascading Unknown Detection With Known Classification For Open Set Recognition ». Dans 2024 IEEE International Conference on Image Processing (ICIP), 652–58. IEEE, 2024. http://dx.doi.org/10.1109/icip51287.2024.10648239.
Texte intégral
2
Che, Yongjuan, Yuexuan An et Hui Xue. « Boosting Few-Shot Open-Set Recognition with Multi-Relation Margin Loss ». Dans Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California : International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/390.
Texte intégralRésumé :
Few-shot open-set recognition (FSOSR) has become a great challenge, which requires classifying known classes and rejecting the unknown ones with only limited samples. Existing FSOSR methods mainly construct an ambiguous distribution of known classes from scarce known samples without considering the latent distribution information of unknowns, which degrades the performance of open-set recognition. To address this issue, we propose a novel loss function called multi-relation margin (MRM) loss that can plug in few-shot methods to boost the performance of FSOSR. MRM enlarges the margin between different classes by extracting the multi-relationship of paired samples to dynamically refine the decision boundary for known classes and implicitly delineate the distribution of unknowns. Specifically, MRM separates the classes by enforcing a margin while concentrating samples of the same class on a hypersphere with a learnable radius. In order to better capture the distribution information of each class, MRM extracts the similarity and correlations among paired samples, ameliorating the optimization of the margin and radius. Experiments on public benchmarks reveal that methods with MRM loss can improve the unknown detection of AUROC by a significant margin while correctly classifying the known classes.
3
Haoyang, Liu, Yaojin Lin, Peipei Li, Jun Hu et Xuegang Hu. « Class-Specific Semantic Generation and Reconstruction Learning for Open Set Recognition ». Dans Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}. California : International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/ijcai.2024/226.
Texte intégralRésumé :
Open set recognition is a crucial research theme for open-environment machine learning. For this problem, a common solution is to learn compact representations of known classes and identify unknown samples by measuring deviations from these known classes. However, the aforementioned methods (1) lack open training consideration, which is detrimental to the fitting of known classes, and (2) recognize unknown classes on an inadequate basis, which limits the accuracy of recognition. In this study, we propose an open reconstruction learning framework that learns a union boundary region of known classes to characterize unknown space. This facilitates the isolation of known space from unknown space to represent known classes compactly and provides a more reliable recognition basis from the perspective of both known and unknown space. Specifically, an adversarial constraint is used to generate class-specific boundary samples. Then, the known classes and approximate unknown space are fitted with manifolds represented by class-specific auto-encoders. Finally, the auto-encoders output the reconstruction error in terms of known and unknown spaces to recognize samples. Extensive experimental results show that the proposed method outperforms existing advanced methods and achieves new stateof-the-art performance. The code is available at https://github.com/Ashowman98/CSGRL.
4
Xu, Shuyuan, Linsen Li, Hangjun Yang et Junhua Tang. « KCC Method : Unknown Intrusion Detection Based on Open Set Recognition ». Dans 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2021. http://dx.doi.org/10.1109/ictai52525.2021.00213.
Texte intégral
5
Yang, Haifeng, Chuanxing Geng, Pong C. Yuen et Songcan Chen. « Dynamic against Dynamic : An Open-Set Self-Learning Framework ». Dans Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}. California : International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/ijcai.2024/587.
Texte intégralRésumé :
In open set recognition, existing methods generally learn statically fixed decision boundaries to reject unknown classes. Though they have achieved promising results, such decision boundaries are evidently insufficient for universal unknown classes in dynamic and open scenarios as they can potentially appear at any position in the feature space. Moreover, these methods just simply reject unknown class samples during testing without any effective utilization for them. In fact, such samples completely can constitute the true instantiated representation of the unknown classes to further enhance the model's performance. To address these issues, this paper proposes a novel dynamic against dynamic idea, i.e., dynamic method against dynamic changing open-set world, where an open-set self-learning (OSSL) framework is correspondingly developed. OSSL starts with a good closed-set classifier trained by known classes and utilizes available test samples for model adaptation during testing, thus gaining the adaptability to changing data distributions. In particular, a novel self-matching module is designed for OSSL, which can achieve the adaptation in automatically identifying known class samples while rejecting unknown class samples which are further utilized to enhance the discriminability of the model as the instantiated representation of unknown classes. Our method establishes new performance milestones respectively in almost all standard and cross-data benchmarks.
6
Zhang, Qin, Zelin Shi, Xiaolin Zhang, Xiaojun Chen, Philippe Fournier-Viger et Shirui Pan. « G2Pxy : Generative Open-Set Node Classification on Graphs with Proxy Unknowns ». Dans Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California : International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/509.
Texte intégralRésumé :
Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training. But in real-life, models are of ten applied on data with new classes, which can lead to massive misclassification and thus significantly degrade performance. Hence, developing open-set classification methods is crucial to determine if a given sample belongs to a known class. Existing methods for open-set node classification generally use transductive learning with part or all of the features of real unseen class nodes to help with open-set classification. In this paper, we propose a novel generative open-set node classification method, i.e., G2Pxy, which follows a stricter inductive learning setting where no information about unknown classes is available during training and validation. Two kinds of proxy unknown nodes, inter-class unknown proxies and external unknown proxies are generated via mixup to efficiently anticipate the distribution of novel classes. Using the generated proxies, a closed-set classifier can be transformed into an open-set one, by augmenting it with an extra proxy classifier. Under the constraints of both cross entropy loss and complement entropy loss, G2Pxy achieves superior effectiveness for unknown class detection and known class classification, which is validated by experiments on bench mark graph datasets. Moreover, G2Pxy does not have specific requirement on the GNN architecture and shows good generalizations.
7
Loboda, Igor, Juan Luis Pérez-Ruiz, Sergiy Yepifanov et Roman Zelenskyi. « Comparative Analysis of Two Gas Turbine Diagnosis Approaches ». Dans ASME Turbo Expo 2019 : Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/gt2019-91644.
Texte intégralRésumé :
Abstract Gas turbine diagnostics that relies on gas path measurements is a well-developed area with many algorithms developed. They follow two general approaches, data-driven, and physics-based. The first approach uses deviations of monitored variables from their baseline values. A diagnostic decision is traditionally made in the space of these deviations (diagnostic features) by pattern recognition techniques, for example, artificial neural networks. The necessary fault classes can be constructed from deviation vectors (patterns) using the displays of real faults, and the approach has a theoretical possibility to exclude a complex physics-based model and its inherent errors from a diagnostic process. For the second approach known as a gas path analysis, a nonlinear physics-based model (a.k.a. thermodynamic model) is an integral part of a diagnostic process. The thermodynamic model (or the corresponding linear model) relates monitored variables with operational conditions and model’s internal quantities called fault parameters. The identification of the thermodynamic model on the basis of known measurements of the monitored variables and operational conditions allows estimating unknown fault parameters. The knowledge of these parameters drastically simplifies a final diagnostic decision because great values of these parameters indicate damaged engine components and give us the measure of damage severity. As the diagnostic decision seems to be simple, the studies following this approach are usually completed by the analysis of fault parameter estimation accuracy, and complex pattern recognition techniques are not employed. Instead, simple tolerance-based fault detection and isolation is sometimes performed. It is not clear from known comparative studies which of the two approaches is more accurate, and the issue of seems to be challenging. This paper tries to solve this problem, being grounded on the following principles. We consider that a key difference of the second approach is a transformation from the diagnostic space of the deviations of monitored variables to the space of fault parameters. To evaluate the influence of this transformation on diagnostic accuracy, the other steps of the approaches should be equal. To this end, the pattern recognition technique employed in the data-driven approach is also included in the physics-based approach where it is applied to recognize fault parameter patterns instead of a tolerance-based rule. To realize and compare the data-driven and modified physics-based approaches, two corresponding diagnostic procedures differing only by the mentioned transformation have been developed. They use the same set of deviation vectors of healthy and faulty engines as input data and finally compute true classification rates that are employed to compare the procedures. The results obtained for different cases of the present comparative study show that the classification rates are practically the same for these procedures, and this is true for both fault detection and fault isolation. That is, correct classification does not depend on the mentioned transformation, and both approaches are equal from the standpoint of the classification accuracy of engine states.
8
Nunes, Ian, Hugo Oliveira et Marcus Poggi. « Open-set semantic segmentation for remote sensing images ». Dans Anais Estendidos da Conference on Graphics, Patterns and Images, 22–28. Sociedade Brasileira de Computação - SBC, 2024. https://doi.org/10.5753/sibgrapi.est.2024.31640.
Texte intégralRésumé :
Collecting samples that exhaust all possible classes for real-world tasks is usually difficult or impossible due to many different factors. In a realistic/feasible scenario, methods should be aware that the training data is incomplete and that not all knowledge is available. Therefore all developed methods should be able to identify the unknown samples while correctly executing the proposed task to the known classes in the tests phase. Open-Set Recognition and Semantic Segmentation models emerge to handle this kind of scenario for, respectively, visual recognition and dense labeling tasks. Initially, this work proposes a novel taxonomy aiming to organize the literature and provide an understanding of the theoretical trends that guided the existing approaches that may influence future methods. This work also proposes two distinct techniques to perform open-set semantic segmentation. First, a method called Open Gaussian Mixture of Models (OpenGMM) extends the Open Principal Component Scoring (OpenPCS) framework using a Gaussian Mixture of Models to model the distribution of pixels for each class in a multimodal manner. Second, the Conditional Reconstruction for Open-set Semantic Segmentation (CoReSeg) method tackles the issue using class-conditioned reconstruction of the input images according to their pixel-wise mask. The third proposed approach is a general post-processing procedure that uses superpixels to enforce highly homogeneous regions to behave equally, rectifying erroneously classified pixels within these regions. We also proposed a novel superpixel generation method called Fusing Superpixels for Semantic Consistency (FuSC). All proposed approaches produce better semantic consistency and outperformed state-of-the-art baseline methods on Vaihingen and Potsdam ISPRS dataset. The official implementation of all proposed approaches is available at https://github.com/iannunes.
9
Liu, Jiaming, Yangqiming Wang, Tongze Zhang, Yulu Fan, Qinli Yang et Junming Shao. « Open-world Semi-supervised Novel Class Discovery ». Dans Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California : International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/445.
Texte intégralRésumé :
Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in the unlabeled set. Therefore, it is of great challenge to not only recognize samples from known classes but also discover the unknown number of novel classes within the unlabeled data. In this paper, we introduce a new open-world semi-supervised novel class discovery approach named OpenNCD, a progressive bi-level contrastive learning method over multiple prototypes. The proposed method is composed of two reciprocally enhanced parts. First, a bi-level contrastive learning method is introduced, which maintains the pair-wise similarity of the prototypes and the prototype group levels for better representation learning. Then, a reliable prototype similarity metric is proposed based on the common representing instances. Prototypes with high similarities will be grouped progressively for known class recognition and novel class discovery. Extensive experiments on three image datasets are conducted and the results show the effectiveness of the proposed method in open-world scenarios, especially with scarce known classes and labels.