Self-supervisedly Augmented Supervised Classification Enhancement
Author:
Affiliation:

Clc Number:

TP181

  • Article
  • | |
  • Metrics
  • |
  • Reference [27]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    With the free supervised signals/labels created by pretext tasks, self-supervised learning (SSL) can learn effective representation from unlabeled data, which has been verified in various downstream tasks. Existing pretext tasks usually first perform explicit linear or nonlinear transformations on the original view data, thus forming multiple augmented view data, then learn the representation by predicting the corresponding transformations or maximizing the consistency among the above views. It is found that such self-supervised augmentations (i.e., the augmentations of the data itself and self-supervised labels) benefit the learning of not only the unsupervised pretext tasks but also the supervised classification task. Nevertheless, few work focus on this at present, while existing works either take the pretexts as the auxiliary of downstream classification task and adopt the multi-task learning or jointly model the downstream task labels and self-supervised labels in a multi-label learning way. Actually, there are inherent differences between downstream and pretext tasks (e.g., semantic, task difficulty, etc.), which inevitably result in the competitions between them and bring risks to the learning of downstream tasks. To challenge this issue, this study proposes a simple yet effective SSL multi-view learning framework (SSL-MV), which avoids the learning interference of self-supervised labels on downstream labels through performing the same learning as downstream tasks on the augmented data views. More interestingly, with the multi-view learning, the proposed framework naturally owns the integration inference ability, which significantly improves the performance of downstream supervised classification tasks. Extensive experiments on benchmark datasets demonstrate the effectiveness of SSL-MV.

    Reference
    [1] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc. of the IEEE, 1998, 86(11):2278-2324.[doi:10.1109/5.726791]
    [2] Figueiredo MAT, Jain AK. Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3):381-396.[doi:10.1109/34.990138]
    [3] Jing LL, Tian YL. Self-supervised visual feature learning with deep neural networks:A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(11):4037-4058.[doi:10.1109/TPAMI.2020.2992393]
    [4] Ericsson L, Gouk H, Hospedales TM. How well do self-supervised models transfer? In:Proc. of the 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Nashville:IEEE, 2021. 5410-5419.
    [5] Wang Z, Chen SC, Gao DQ. A novel multi-view learning developed from single-view patterns. Pattern Recognition, 2011, 44(10-11):2395-2413.
    [6] Wang Z, Xu J, Chen SC, Gao DQ. Regularized multi-view learning machine based on response surface technique. Neurocomputing, 2012, 97:201-213.[doi:10.1016/j.neucom.2012.05.027]
    [7] 赵博宇, 张长青, 陈蕾, 刘新旺, 李泽超, 胡清华. 生成式不完整多视图数据聚类. 自动化学报, 2021, 47(8):1867-1875.[doi:10.16383/j.aas.c200121] Zhao BY, Zhang CQ, Chen L, Liu XW, Li ZC, Hu QH. Generative model for partial multi-view clustering. Acta Automatica Sinica, 2021, 47(8):1867-1875(in Chinese with English abstract).[doi:10.16383/j.aas.c200121]
    [8] Gidaris S, Singh P, Komodakis N. Unsupervised representation learning by predicting image rotations. In:Proc. of the 2018 Int'l Conf. on Learning Representations (ICLR). Vancouver:OpenReview.net, 2018.
    [9] Noroozi M, Favaro P. Unsupervised learning of visual representations by solving jigsaw puzzles. In:Proc. of the 14th European Conf. on Computer Vision. Amsterdam:Springer, 2016. 69-84.
    [10] Chen T, Kornblith S, Norouzi M, Hinton G. A simple framework for contrastive learning of visual representations. In:Proc. of the 37th Int'l Conf. on Machine Learning. Vienna:PMLR, 2020. 1597-1607.
    [11] He KM, Fan HQ, Wu YX, Xie SN, Girshick R. Momentum contrast for unsupervised visual representation learning. In:Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle:IEEE, 2020. 9726-9735.
    [12] Caron M, Misra I, Mairal J, Goyal P, Bojanowski P, Joulin A. Unsupervised learning of visual features by contrasting cluster assignments. Advances in Neural Information Processing Systems. 2020.
    [13] Caron M, Bojanowski P, Joulin A, Douze M. Deep clustering for unsupervised learning of visual features. In:Proc. of the 15th European Conf. on Computer Vision. Munich:Springer, 2018. 139-156.
    [14] Asano YM, Rupprecht C, Vedaldi A. Self-labelling via simultaneous clustering and representation learning. In:Proc. of the 2019 Int'l Conf. on Learning Representations (ICLR). Addis Ababa, Ethiopia:OpenReview.net, 2019.
    [15] Sun Y, Tzeng E, Darrell T, Efros AA. Unsupervised domain adaptation through self-supervision. arXiv:1909.11825, 2019.
    [16] Hendrycks D, Mazeika M, Kadavath S, Song D. Using self-supervised learning can improve model robustness and uncertainty. Advances in Neural Information Processing Systems. Vancouver, 2019.
    [17] Tack J, Mo S, Jeong J, Shin, J. CSI:Novelty detection via contrastive learning on distributionally shifted instances. Advances in Neural Information Processing Systems. 2020.
    [18] Zhong Z, Zheng L, Kang GL, Li SZ, Yang Y. Random erasing data augmentation. Proc. of the AAAI Conf. on Artificial Intelligence, 2020, 34(7):13001-13008.[doi:10.1609/aaai.v34i07.7000]
    [19] 黄凯奇, 任伟强, 谭铁牛. 图像物体分类与检测算法综述. 计算机学报, 2014, 37(6):1225-1240.[doi:10.3724/SP.J.1016.2014.01225] Huang KQ, Ren WQ, Tan TN. A review on image object classification and detection. Chinese Journal of Computers, 2014, 37(6):1225-1240(in Chinese with English abstract).[doi:10.3724/SP.J.1016.2014.01225]
    [20] Lee H, Hwang SJ, Shin J. Self-supervised label augmentation via input transformations. In:Proc. of the 37th Int'l Conf. on Machine Learning. PMLR, 2020. 5714-5724.
    [21] 谭正豪. 关于深度学习中的一些策略泛化性能的研究[硕士学位论文]. 南京:南京航空航天大学, 2021. Tan ZH. On the generalization ability of deep learning strategies[MS. Thesis]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2021(in Chinese with English abstract).
    [22] Krizhevsky A. Learning multiple layers of features from tiny images. Technical Report, Toronto:University of Toronto, 2009.
    [23] Le Y, Yang X. Tiny imagenet visual recognition challenge. CS 231N7, 2015. http://cs231n.stanford.edu/reports/2015/pdfs/yle_project.pdf
    [24] Quattoni A, Torralba A. Recognizing indoor scenes. In:Proc. of the 2009 IEEE Conf. on Computer Vision and Pattern Recognition. Miami:IEEE, 2009. 413-420.
    [25] He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. In:Proc. of the 2016 IEEE Conf. on Computer Vision and Pattern Recognition. Las Vegas:IEEE, 2016. 770-778.
    [26] Bengio Y. Deep learning of representations:Looking forward. In:Proc. of the 1st Int'l Conf. on Statistical Language and Speech Proc. Tarragona:Springer, 2013. 1-37.
    [27] Geng CX, Huang SJ, Chen SC. Recent advances in open set recognition:A survey. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2021, 43(10):3614-3631.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

耿传兴,谭正豪,陈松灿.自监督增广的监督分类学习增强.软件学报,2023,34(4):1870-1878

Copy
Share
Article Metrics
  • Abstract:753
  • PDF: 2441
  • HTML: 1384
  • Cited by: 0
History
  • Received:June 07,2021
  • Revised:July 17,2021
  • Online: September 30,2022
  • Published: April 06,2023
You are the first2038098Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063