Journal articles: 'Self-supervised learninig'

1

Zhao, Qingyu, Zixuan Liu, Ehsan Adeli, and Kilian M. Pohl. "Longitudinal self-supervised learning." Medical Image Analysis 71 (July 2021): 102051. http://dx.doi.org/10.1016/j.media.2021.102051.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Wang, Fei, and Changshui Zhang. "Robust self-tuning semi-supervised learning." Neurocomputing 70, no. 16-18 (October 2007): 2931–39. http://dx.doi.org/10.1016/j.neucom.2006.11.004.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Hrycej, Tomas. "Supporting supervised learning by self-organization." Neurocomputing 4, no. 1-2 (February 1992): 17–30. http://dx.doi.org/10.1016/0925-2312(92)90040-v.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Shin, Sungho, Jongwon Kim, Yeonguk Yu, Seongju Lee, and Kyoobin Lee. "Self-Supervised Transfer Learning from Natural Images for Sound Classification." Applied Sciences 11, no. 7 (March 29, 2021): 3043. http://dx.doi.org/10.3390/app11073043.

Full text

Abstract:

We propose the implementation of transfer learning from natural images to audio-based images using self-supervised learning schemes. Through self-supervised learning, convolutional neural networks (CNNs) can learn the general representation of natural images without labels. In this study, a convolutional neural network was pre-trained with natural images (ImageNet) via self-supervised learning; subsequently, it was fine-tuned on the target audio samples. Pre-training with the self-supervised learning scheme significantly improved the sound classification performance when validated on the following benchmarks: ESC-50, UrbanSound8k, and GTZAN. The network pre-trained via self-supervised learning achieved a similar level of accuracy as those pre-trained using a supervised method that require labels. Therefore, we demonstrated that transfer learning from natural images contributes to improvements in audio-related tasks, and self-supervised learning with natural images is adequate for pre-training scheme in terms of simplicity and effectiveness.

APA, Harvard, Vancouver, ISO, and other styles

5

Liu, Yuanyuan, and Qianqian Liu. "Research on Self-Supervised Comparative Learning for Computer Vision." Journal of Electronic Research and Application 5, no. 3 (August 17, 2021): 5–17. http://dx.doi.org/10.26689/jera.v5i3.2320.

Full text

Abstract:

In recent years, self-supervised learning which does not require a large number of manual labels generate supervised signals through the data itself to attain the characterization learning of samples. Self-supervised learning solves the problem of learning semantic features from unlabeled data, and realizes pre-training of models in large data sets. Its significant advantages have been extensively studied by scholars in recent years. There are usually three types of self-supervised learning: “Generative, Contrastive, and Generative-Contrastive.” The model of the comparative learning method is relatively simple, and the performance of the current downstream task is comparable to that of the supervised learning method. Therefore, we propose a conceptual analysis framework: data augmentation pipeline, architectures, pretext tasks, comparison methods, semi-supervised fine-tuning. Based on this conceptual framework, we qualitatively analyze the existing comparative self-supervised learning methods for computer vision, and then further analyze its performance at different stages, and finally summarize the research status of self-supervised comparative learning methods in other fields.

APA, Harvard, Vancouver, ISO, and other styles

6

Jaiswal, Ashish, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Debapriya Banerjee, and Fillia Makedon. "A Survey on Contrastive Self-Supervised Learning." Technologies 9, no. 1 (December 28, 2020): 2. http://dx.doi.org/10.3390/technologies9010002.

Full text

Abstract:

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.

APA, Harvard, Vancouver, ISO, and other styles

7

ITO, Seiya, Naoshi KANEKO, and Kazuhiko SUMI. "Self-Supervised Learning for Multi-View Stereo." Journal of the Japan Society for Precision Engineering 86, no. 12 (December 5, 2020): 1042–50. http://dx.doi.org/10.2493/jjspe.86.1042.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Tenorio, M. F., and W. T. Lee. "Self-organizing network for optimum supervised learning." IEEE Transactions on Neural Networks 1, no. 1 (March 1990): 100–110. http://dx.doi.org/10.1109/72.80209.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Florence, Peter, Lucas Manuelli, and Russ Tedrake. "Self-Supervised Correspondence in Visuomotor Policy Learning." IEEE Robotics and Automation Letters 5, no. 2 (April 2020): 492–99. http://dx.doi.org/10.1109/lra.2019.2956365.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Liu, Chicheng, Libin Song, Jiwen Zhang, Ken Chen, and Jing Xu. "Self-Supervised Learning for Specified Latent Representation." IEEE Transactions on Fuzzy Systems 28, no. 1 (January 2020): 47–59. http://dx.doi.org/10.1109/tfuzz.2019.2904237.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Pal, S. K., A. Pathak, and C. Basu. "Dynamic guard zone for self-supervised learning." Pattern Recognition Letters 7, no. 3 (March 1988): 135–44. http://dx.doi.org/10.1016/0167-8655(88)90056-6.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Hayat, Md Abul, George Stein, Peter Harrington, Zarija Lukić, and Mustafa Mustafa. "Self-supervised Representation Learning for Astronomical Images." Astrophysical Journal Letters 911, no. 2 (April 1, 2021): L33. http://dx.doi.org/10.3847/2041-8213/abf2c7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Che, Feihu, Guohua Yang, Dawei Zhang, Jianhua Tao, and Tong Liu. "Self-supervised graph representation learning via bootstrapping." Neurocomputing 456 (October 2021): 88–96. http://dx.doi.org/10.1016/j.neucom.2021.03.123.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Tripathi, Achyut Mani, and Aakansha Mishra. "Self-supervised learning for Environmental Sound Classification." Applied Acoustics 182 (November 2021): 108183. http://dx.doi.org/10.1016/j.apacoust.2021.108183.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Islam, Md Rabiul, Shuji Sakamoto, Yoshihiro Yamada, Andrew W. Vargo, Motoi Iwata, Masakazu Iwamura, and Koichi Kise. "Self-supervised Learning for Reading Activity Classification." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, no. 3 (September 9, 2021): 1–22. http://dx.doi.org/10.1145/3478088.

Full text

Abstract:

Reading analysis can relay information about user's confidence and habits and can be used to construct useful feedback. A lack of labeled data inhibits the effective application of fully-supervised Deep Learning (DL) for automatic reading analysis. We propose a Self-supervised Learning (SSL) method for reading analysis. Previously, SSL has been effective in physical human activity recognition (HAR) tasks, but it has not been applied to cognitive HAR tasks like reading. We first evaluate the proposed method on a four-class classification task on reading detection using electrooculography datasets, followed by an evaluation of a two-class classification task of confidence estimation on multiple-choice questions using eye-tracking datasets. Fully-supervised DL and support vector machines (SVMs) are used as comparisons for the proposed SSL method. The results show that the proposed SSL method is superior to the fully-supervised DL and SVM for both tasks, especially when training data is scarce. This result indicates the proposed method is the superior choice for reading analysis tasks. These results are important for informing the design of automatic reading analysis platforms.

APA, Harvard, Vancouver, ISO, and other styles

16

Li, Jingwei, Chi Zhang, Linyuan Wang, Penghui Ding, Lulu Hu, Bin Yan, and Li Tong. "A Visual Encoding Model Based on Contrastive Self-Supervised Learning for Human Brain Activity along the Ventral Visual Stream." Brain Sciences 11, no. 8 (July 29, 2021): 1004. http://dx.doi.org/10.3390/brainsci11081004.

Full text

Abstract:

Visual encoding models are important computational models for understanding how information is processed along the visual stream. Many improved visual encoding models have been developed from the perspective of the model architecture and the learning objective, but these are limited to the supervised learning method. From the view of unsupervised learning mechanisms, this paper utilized a pre-trained neural network to construct a visual encoding model based on contrastive self-supervised learning for the ventral visual stream measured by functional magnetic resonance imaging (fMRI). We first extracted features using the ResNet50 model pre-trained in contrastive self-supervised learning (ResNet50-CSL model), trained a linear regression model for each voxel, and finally calculated the prediction accuracy of different voxels. Compared with the ResNet50 model pre-trained in a supervised classification task, the ResNet50-CSL model achieved an equal or even relatively better encoding performance in multiple visual cortical areas. Moreover, the ResNet50-CSL model performs hierarchical representation of input visual stimuli, which is similar to the human visual cortex in its hierarchical information processing. Our experimental results suggest that the encoding model based on contrastive self-supervised learning is a strong computational model to compete with supervised models, and contrastive self-supervised learning proves an effective learning method to extract human brain-like representations.

APA, Harvard, Vancouver, ISO, and other styles

17

Nartey, Obed Tettey, Guowu Yang, Sarpong Kwadwo Asare, Jinzhao Wu, and Lady Nadia Frempong. "Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning." Sensors 20, no. 9 (May 8, 2020): 2684. http://dx.doi.org/10.3390/s20092684.

Full text

Abstract:

Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms. Although both computer vision and machine learning techniques have constantly been improved to solve this problem, the sudden rise in the number of unlabeled traffic signs has become even more challenging. Large data collation and labeling are tedious and expensive tasks that demand much time, expert knowledge, and fiscal resources to satisfy the hunger of deep neural networks. Aside from that, the problem of having unbalanced data also poses a greater challenge to computer vision and machine learning algorithms to achieve better performance. These problems raise the need to develop algorithms that can fully exploit a large amount of unlabeled data, use a small amount of labeled samples, and be robust to data imbalance to build an efficient and high-quality classifier. In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data. The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection algorithm to generate and select pseudo-labeled samples. The method improves the performance by: (1) normalizing the class-wise confidence levels to prevent the model from ignoring hard-to-learn samples, thereby solving the imbalanced data problem; (2) jointly learning a model and optimizing pseudo-labels generated on unlabeled data; and (3) enlarging the training set to satisfy the hunger of deep learning models. Extensive evaluations on two public traffic sign recognition datasets demonstrate the effectiveness of the proposed technique and provide a potential solution for practical applications.

APA, Harvard, Vancouver, ISO, and other styles

18

Zhou, Meng, Zechen Li, and Pengtao Xie. "Self-supervised Regularization for Text Classification." Transactions of the Association for Computational Linguistics 9 (2021): 641–56. http://dx.doi.org/10.1162/tacl_a_00389.

Full text

Abstract:

Abstract Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL (Devlin et al., 2019a) is an unsupervised learning approach that defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human- provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg.

APA, Harvard, Vancouver, ISO, and other styles

19

Li, Li, Kaiyi Zhao, Sicong Li, Ruizhi Sun, and Saihua Cai. "Extreme Learning Machine for Supervised Classification with Self-paced Learning." Neural Processing Letters 52, no. 3 (June 14, 2020): 1723–44. http://dx.doi.org/10.1007/s11063-020-10286-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

C A Padmanabha Reddy, Y., P. Viswanath, and B. Eswara Reddy. "Semi-supervised learning: a brief review." International Journal of Engineering & Technology 7, no. 1.8 (February 9, 2018): 81. http://dx.doi.org/10.14419/ijet.v7i1.8.9977.

Full text

Abstract:

Most of the application domain suffers from not having sufficient labeled data whereas unlabeled data is available cheaply. To get labeled instances, it is very difficult because experienced domain experts are required to label the unlabeled data patterns. Semi-supervised learning addresses this problem and act as a half way between supervised and unsupervised learning. This paper addresses few techniques of Semi-supervised learning (SSL) such as self-training, co-training, multi-view learning, TSVMs methods. Traditionally SSL is classified in to Semi-supervised Classification and Semi-supervised Clustering which achieves better accuracy than traditional supervised and unsupervised learning techniques. The paper also addresses the issue of scalability and applications of Semi-supervised learning.

APA, Harvard, Vancouver, ISO, and other styles

21

Wang, Shaolei, Wangxiang Che, Qi Liu, Pengda Qin, Ting Liu, and William Yang Wang. "Multi-Task Self-Supervised Learning for Disfluency Detection." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 9193–200. http://dx.doi.org/10.1609/aaai.v34i05.6456.

Full text

Abstract:

Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled news data, and propose two self-supervised pre-training tasks: (i) tagging task to detect the added noisy words. (ii) sentence classification to distinguish original sentences from grammatically-incorrect sentences. We then combine these two tasks to jointly train a network. The pre-trained network is then fine-tuned using human-annotated disfluency detection training data. Experimental results on the commonly used English Switchboard test set show that our approach can achieve competitive performance compared to the previous systems (trained using the full dataset) by using less than 1% (1000 sentences) of the training data. Our method trained on the full dataset significantly outperforms previous methods, reducing the error by 21% on English Switchboard.

APA, Harvard, Vancouver, ISO, and other styles

22

Fazakis, Nikos, Stamatis Karlos, Sotiris Kotsiantis, and Kyriakos Sgarbas. "Self-trained Rotation Forest for semi-supervised learning." Journal of Intelligent & Fuzzy Systems 32, no. 1 (January 13, 2017): 711–22. http://dx.doi.org/10.3233/jifs-152641.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Zhao, Qilu, and Junyu Dong. "Self-supervised representation learning by predicting visual permutations." Knowledge-Based Systems 210 (December 2020): 106534. http://dx.doi.org/10.1016/j.knosys.2020.106534.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Sharma, Vivek, Makarand Tapaswi, M. Saquib Sarfraz, and Rainer Stiefelhagen. "Video Face Clustering With Self-Supervised Representation Learning." IEEE Transactions on Biometrics, Behavior, and Identity Science 2, no. 2 (April 2020): 145–57. http://dx.doi.org/10.1109/tbiom.2019.2947264.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Gan, Jiangzhang, Guoqiu Wen, Hao Yu, Wei Zheng, and Cong Lei. "Supervised feature selection by self-paced learning regression." Pattern Recognition Letters 132 (April 2020): 30–37. http://dx.doi.org/10.1016/j.patrec.2018.08.029.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Zeng, Zeng, Yang Xulei, Yu Qiyun, Yao Meng, and Zhang Le. "SeSe-Net: Self-Supervised deep learning for segmentation." Pattern Recognition Letters 128 (December 2019): 23–29. http://dx.doi.org/10.1016/j.patrec.2019.08.002.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Schmidt, Tanner, Richard Newcombe, and Dieter Fox. "Self-Supervised Visual Descriptor Learning for Dense Correspondence." IEEE Robotics and Automation Letters 2, no. 2 (April 2017): 420–27. http://dx.doi.org/10.1109/lra.2016.2634089.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Hu, Fanghuai, Zhiqing Shao, and Tong Ruan. "Self-Supervised Chinese Ontology Learning from Online Encyclopedias." Scientific World Journal 2014 (2014): 1–13. http://dx.doi.org/10.1155/2014/848631.

Full text

Abstract:

Constructing ontology manually is a time-consuming, error-prone, and tedious task. We present SSCO, a self-supervised learning based chinese ontology, which contains about 255 thousand concepts, 5 million entities, and 40 million facts. We explore the three largest online Chinese encyclopedias for ontology learning and describe how to transfer the structured knowledge in encyclopedias, including article titles, category labels, redirection pages, taxonomy systems, and InfoBox modules, into ontological form. In order to avoid the errors in encyclopedias and enrich the learnt ontology, we also apply some machine learning based methods. First, we proof that the self-supervised machine learning method is practicable in Chinese relation extraction (at least for synonymy and hyponymy) statistically and experimentally and train some self-supervised models (SVMs and CRFs) for synonymy extraction, concept-subconcept relation extraction, and concept-instance relation extraction; the advantages of our methods are that all training examples are automatically generated from the structural information of encyclopedias and a few general heuristic rules. Finally, we evaluate SSCO in two aspects, scale and precision; manual evaluation results show that the ontology has excellent precision, and high coverage is concluded by comparing SSCO with other famous ontologies and knowledge bases; the experiment results also indicate that the self-supervised models obviously enrich SSCO.

APA, Harvard, Vancouver, ISO, and other styles

29

Sofman, Boris, Ellie Lin, J. Andrew Bagnell, John Cole, Nicolas Vandapel, and Anthony Stentz. "Improving robot navigation through self-supervised online learning." Journal of Field Robotics 23, no. 11-12 (November 2006): 1059–75. http://dx.doi.org/10.1002/rob.20169.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Chen, Yajing, Fanzi Wu, Zeyu Wang, Yibing Song, Yonggen Ling, and Linchao Bao. "Self-Supervised Learning of Detailed 3D Face Reconstruction." IEEE Transactions on Image Processing 29 (2020): 8696–705. http://dx.doi.org/10.1109/tip.2020.3017347.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Guizilini, Vitor, and Fabio Ramos. "Online self-supervised learning for dynamic object segmentation." International Journal of Robotics Research 34, no. 4-5 (March 25, 2015): 559–81. http://dx.doi.org/10.1177/0278364914566514.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Decoux, Benoît. "Self-Supervised Learning in Cooperative Stereo Vision Correspondence." International Journal of Neural Systems 08, no. 01 (February 1997): 101–11. http://dx.doi.org/10.1142/s0129065797000136.

Full text

Abstract:

This paper presents a neural network model of stereoscopic vision, in which a process of fusion seeks the correspondence between points of stereo inputs. Stereo fusion is obtained after a self-supervised learning phase, so called because the learning rule is a supervised-learning rule in which the supervisory information is autonomously extracted from the visual inputs by the model. This supervisory information arises from a global property of the potential matches between the points. The proposed neural network, which is of the cooperative type, and the learning procedure, are tested with random-dot stereograms (RDS) and feature points extracted from real-world images. Those feature points are extracted by a technique based on the use of sigma-pi units. The matching performance and the generalization ability of the model are quantified. The relationship between what have been learned by the network and the constraints used in previous cooperative models of stereo vision, is discussed.

APA, Harvard, Vancouver, ISO, and other styles

33

Karlos, Stamatis, Nikos Fazakis, Sotiris Kotsiantis, and Kyriakos Sgarbas. "Self-Trained Stacking Model for Semi-Supervised Learning." International Journal on Artificial Intelligence Tools 26, no. 02 (April 2017): 1750001. http://dx.doi.org/10.1142/s0218213017500014.

Full text

Abstract:

The most important characteristic of semi-supervised learning methods is the combination of available unlabeled data along with an enough smaller set of labeled examples, so as to increase the learning accuracy compared with the default procedure of supervised methods, which on the other hand use only the labeled data during the training phase. In this work, we have implemented a hybrid Self-trained system that combines a Support Vector Machine, a Decision Tree, a Lazy Learner and a Bayesian algorithm using a Stacking variant methodology. We performed an in depth comparison with other well-known Semi-Supervised classification methods on standard benchmark datasets and we finally reached to the point that the presented technique had better accuracy in most cases.

APA, Harvard, Vancouver, ISO, and other styles

34

Cooperstock, Jeremy R., and Evangelos E. Milios. "Self-supervised learning for docking and target reaching." Robotics and Autonomous Systems 11, no. 3-4 (December 1993): 243–60. http://dx.doi.org/10.1016/0921-8890(93)90029-c.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Huang, Jiancong, Juan Rojas, Matthieu Zimmer, Hongmin Wu, Yisheng Guan, and Paul Weng. "Hyperparameter Auto-Tuning in Self-Supervised Robotic Learning." IEEE Robotics and Automation Letters 6, no. 2 (April 2021): 3537–44. http://dx.doi.org/10.1109/lra.2021.3064509.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

She, Dong-Yu, and Kun Xu. "Contrastive Self-supervised Representation Learning Using Synthetic Data." International Journal of Automation and Computing 18, no. 4 (May 11, 2021): 556–67. http://dx.doi.org/10.1007/s11633-021-1297-9.

Full text

Abstract:

AbstractLearning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability. Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.

APA, Harvard, Vancouver, ISO, and other styles

37

Imran, Abdullah-Al-Zubaer, Chao Huang, Hui Tang, Wei Fan, Yuan Xiao, Dingjun Hao, Zhen Qian, and Demetri Terzopoulos. "Self-Supervised, Semi-Supervised, Multi-Context Learning for the Combined Classification and Segmentation of Medical Images (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 10 (April 3, 2020): 13815–16. http://dx.doi.org/10.1609/aaai.v34i10.7179.

Full text

Abstract:

To tackle the problem of limited annotated data, semi-supervised learning is attracting attention as an alternative to fully supervised models. Moreover, optimizing a multiple-task model to learn “multiple contexts” can provide better generalizability compared to single-task models. We propose a novel semi-supervised multiple-task model leveraging self-supervision and adversarial training—namely, self-supervised, semi-supervised, multi-context learning (S4MCL)—and apply it to two crucial medical imaging tasks, classification and segmentation. Our experiments on spine X-rays reveal that the S4MCL model significantly outperforms semi-supervised single-task, semi-supervised multi-context, and fully-supervised single-task models, even with a 50% reduction of classification and segmentation labels.

APA, Harvard, Vancouver, ISO, and other styles

38

Luo, Dezhao, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, and Weiping Wang. "Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 11701–8. http://dx.doi.org/10.1609/aaai.v34i07.6840.

Full text

Abstract:

We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates “blanks” by withholding video clips and then creates “options” by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with “options” and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning. As a target task, it can assess learned representation models in a uniform and interpretable manner. With VCP, we train spatial-temporal representation models (3D-CNNs) and apply such models on action recognition and video retrieval tasks. Experiments on commonly used benchmarks show that the trained models outperform the state-of-the-art self-supervised models with significant margins.

APA, Harvard, Vancouver, ISO, and other styles

39

Livieris, Ioannis, Andreas Kanavos, Vassilis Tampakas, and Panagiotis Pintelas. "An Auto-Adjustable Semi-Supervised Self-Training Algorithm." Algorithms 11, no. 9 (September 14, 2018): 139. http://dx.doi.org/10.3390/a11090139.

Full text

Abstract:

Semi-supervised learning algorithms have become a topic of significant research as an alternative to traditional classification methods which exhibit remarkable performance over labeled data but lack the ability to be applied on large amounts of unlabeled data. In this work, we propose a new semi-supervised learning algorithm that dynamically selects the most promising learner for a classification problem from a pool of classifiers based on a self-training philosophy. Our experimental results illustrate that the proposed algorithm outperforms its component semi-supervised learning algorithms in terms of accuracy, leading to more efficient, stable and robust predictive models.

APA, Harvard, Vancouver, ISO, and other styles

40

Sun, Ke, Zhouchen Lin, and Zhanxing Zhu. "Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5892–99. http://dx.doi.org/10.1609/aaai.v34i04.6048.

Full text

Abstract:

Graph Convolutional Networks (GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised (M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.

APA, Harvard, Vancouver, ISO, and other styles

41

Sarukkai, Ramesh R. "Supervised Networks That Self-Organize Class Outputs." Neural Computation 9, no. 3 (March 1, 1997): 637–48. http://dx.doi.org/10.1162/neco.1997.9.3.637.

Full text

Abstract:

Supervised, neural network, learning algorithms have proved very successful at solving a variety of learning problems; however, they suffer from a common problem of requiring explicit output labels. In this article, it is shown that pattern classification can be achieved, in a multilayered, feedforward, neural network, without requiring explicit output labels, by a process of supervised self-organization. The class projection is achieved by optimizing appropriate within-class uniformity and between-class discernibility criteria. The mapping function and the class labels are developed together iteratively using the derived self organizing backpropagation algorithm. The ability of the self-organizing network to generalize on unseen data is also experimentally evaluated on real data sets and compares favorably with the traditional labeled supervision with neural networks. In addition, interesting features emerge out of the proposed self-organizing supervision, which are absent in conventional approaches.

APA, Harvard, Vancouver, ISO, and other styles

42

Li, Haifeng, Tian Zhang, and Lin Ma. "Confirmation Based Self-Learning Algorithm in LVCSR's Semi-supervised Incremental Learning." Procedia Engineering 29 (2012): 754–59. http://dx.doi.org/10.1016/j.proeng.2012.01.036.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Yin, Chunwu, and Zhanbo Chen. "Developing Sustainable Classification of Diseases via Deep Learning and Semi-Supervised Learning." Healthcare 8, no. 3 (August 24, 2020): 291. http://dx.doi.org/10.3390/healthcare8030291.

Full text

Abstract:

Disease classification based on machine learning has become a crucial research topic in the fields of genetics and molecular biology. Generally, disease classification involves a supervised learning style; i.e., it requires a large number of labelled samples to achieve good classification performance. However, in the majority of the cases, labelled samples are hard to obtain, so the amount of training data are limited. However, many unclassified (unlabelled) sequences have been deposited in public databases, which may help the training procedure. This method is called semi-supervised learning and is very useful in many applications. Self-training can be implemented using high- to low-confidence samples to prevent noisy samples from affecting the robustness of semi-supervised learning in the training process. The deep forest method with the hyperparameter settings used in this paper can achieve excellent performance. Therefore, in this work, we propose a novel combined deep learning model and semi-supervised learning with self-training approach to improve the performance in disease classification, which utilizes unlabelled samples to update a mechanism designed to increase the number of high-confidence pseudo-labelled samples. The experimental results show that our proposed model can achieve good performance in disease classification and disease-causing gene identification.

APA, Harvard, Vancouver, ISO, and other styles

44

Mohseni, Sina, Mandar Pitale, JBS Yadawa, and Zhangyang Wang. "Self-Supervised Learning for Generalizable Out-of-Distribution Detection." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5216–23. http://dx.doi.org/10.1609/aaai.v34i04.5966.

Full text

Abstract:

The real-world deployment of Deep Neural Networks (DNNs) in safety-critical applications such as autonomous vehicles needs to address a variety of DNNs' vulnerabilities, one of which being detecting and rejecting out-of-distribution outliers that might result in unpredictable fatal errors. We propose a new technique relying on self-supervision for generalizable out-of-distribution (OOD) feature learning and rejecting those samples at the inference time. Our technique does not need to pre-know the distribution of targeted OOD samples and incur no extra overheads compared to other methods. We perform multiple image classification experiments and observe our technique to perform favorably against state-of-the-art OOD detection methods. Interestingly, we witness that our method also reduces in-distribution classification risk via rejecting samples near the boundaries of the training set distribution.

APA, Harvard, Vancouver, ISO, and other styles

45

Sheng, Kekai, Weiming Dong, Menglei Chai, Guohui Wang, Peng Zhou, Feiyue Huang, Bao-Gang Hu, Rongrong Ji, and Chongyang Ma. "Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5709–16. http://dx.doi.org/10.1609/aaai.v34i04.6026.

Full text

Abstract:

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet.

APA, Harvard, Vancouver, ISO, and other styles

46

Wu, Guile, Xiatian Zhu, and Shaogang Gong. "Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 12362–69. http://dx.doi.org/10.1609/aaai.v34i07.6921.

Full text

Abstract:

Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain adaptation or one-shot learning. Although they are more scalable than the supervised learning counterparts, relying on a relevant labelled source domain or one labelled tracklet per person initialisation still restricts their scalability in real-world deployments. To alleviate these problems, some recent studies develop unsupervised tracklet association and bottom-up image clustering methods, but they still rely on explicit camera annotation or merely utilise suboptimal global clustering. In this work, we formulate a novel tracklet self-supervised learning (TSSL) method, which is capable of capitalising directly from abundant unlabelled tracklet data, to optimise a feature embedding space for both video and image unsupervised re-id. This is achieved by designing a comprehensive unsupervised learning objective that accounts for tracklet frame coherence, tracklet neighbourhood compactness, and tracklet cluster structure in a unified formulation. As a pure unsupervised learning re-id model, TSSL is end-to-end trainable at the absence of source data annotation, person identity labels, and camera prior knowledge. Extensive experiments demonstrate the superiority of TSSL over a wide variety of the state-of-the-art alternative methods on four large-scale person re-id benchmarks, including Market-1501, DukeMTMC-ReID, MARS and DukeMTMC-VideoReID.

APA, Harvard, Vancouver, ISO, and other styles

47

Ridge, Barry, Aleš Leonardis, Aleš Ude, Miha Deniša, and Danijel Skočaj. "Self-Supervised Online Learning of Basic Object Push Affordances." International Journal of Advanced Robotic Systems 12, no. 3 (January 2015): 24. http://dx.doi.org/10.5772/59654.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Yan, Xiang, Syed Zulqarnain Gilani, Mingtao Feng, Liang Zhang, Hanlin Qin, and Ajmal Mian. "Self-Supervised Learning to Detect Key Frames in Videos." Sensors 20, no. 23 (December 4, 2020): 6941. http://dx.doi.org/10.3390/s20236941.

Full text

Abstract:

Detecting key frames in videos is a common problem in many applications such as video classification, action recognition and video summarization. These tasks can be performed more efficiently using only a handful of key frames rather than the full video. Existing key frame detection approaches are mostly designed for supervised learning and require manual labelling of key frames in a large corpus of training data to train the models. Labelling requires human annotators from different backgrounds to annotate key frames in videos which is not only expensive and time consuming but also prone to subjective errors and inconsistencies between the labelers. To overcome these problems, we propose an automatic self-supervised method for detecting key frames in a video. Our method comprises a two-stream ConvNet and a novel automatic annotation architecture able to reliably annotate key frames in a video for self-supervised learning of the ConvNet. The proposed ConvNet learns deep appearance and motion features to detect frames that are unique. The trained network is then able to detect key frames in test videos. Extensive experiments on UCF101 human action and video summarization VSUMM datasets demonstrates the effectiveness of our proposed method.

APA, Harvard, Vancouver, ISO, and other styles

49

Olley, P., and AK Kochhar†. "Self-supervised learning for an operational knowledge-based system." Computer Integrated Manufacturing Systems 11, no. 4 (October 1998): 297–308. http://dx.doi.org/10.1016/s0951-5240(98)00028-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Sangineto, Enver, Moin Nabi, Dubravko Culibrk, and Nicu Sebe. "Self Paced Deep Learning for Weakly Supervised Object Detection." IEEE Transactions on Pattern Analysis and Machine Intelligence 41, no. 3 (March 1, 2019): 712–25. http://dx.doi.org/10.1109/tpami.2018.2804907.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Self-supervised learninig'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles