Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation

被引:21
|
作者
Guan, Dayan [1 ]
Huang, Jiaxing [1 ]
Xiao, Aoran [1 ]
Lu, Shijian [1 ]
机构
[1] Nanyang Technol Univ, Singtel Cognit & Artificial Intelligence Lab Ente, Singapore, Singapore
关键词
D O I
10.1109/CVPR52688.2022.00973
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent advance of deep neural networks. However, it often suffers from severe class-bias problem while exploring the unlabelled images, largely due to the clear pixel-wise class imbalance in the labelled images. This paper presents an unbiased subclass regularization network (USRN) that alleviates the class imbalance issue by learning class-unbiased segmentation from balanced subclass distributions. We build the balanced subclass distributions by clustering pixels of each original class into multiple subclasses of similar sizes, which provide class-balanced pseudo supervision to regularize the class-biased segmentation. In addition, we design an entropy-based gate mechanism to coordinate learning between the original classes and the clustered subclasses which facilitates subclass regularization effectively by suppressing unconfident subclass predictions. Extensive experiments over multiple public benchmarks show that USRN achieves superior performance as compared with the state-of-the-art.
引用
收藏
页码:9958 / 9968
页数:11
相关论文
共 50 条
  • [31] Semi-supervised semantic segmentation with cross teacher training
    Xiao, Hui
    Li, Dong
    Xu, Hao
    Fu, Shuibo
    Yan, Diqun
    Song, Kangkang
    Peng, Chengbin
    NEUROCOMPUTING, 2022, 508 : 36 - 46
  • [32] Switching Temporary Teachers for Semi-Supervised Semantic Segmentation
    Na, Jaemin
    Ha, Jung-Woo
    Chang, Hyung Jin
    Han, Dongyoon
    Hwang, Wonjun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [33] Adversarial Semi-Supervised Semantic Segmentation with Attention Mechanism
    Yun, Fei
    Yin, Yanjun
    Zhang, Wenxuan
    Zhi, Min
    Computer Engineering and Applications, 2023, 59 (08) : 254 - 262
  • [34] Semi-supervised Learning Methods for Semantic Segmentation of Polyps
    Ines, Adrian
    Dominguez, Cesar
    Heras, Jonathan
    Mata, Eloy
    Pascual, Vico
    ADVANCES IN ARTIFICIAL INTELLIGENCE, CAEPIA 2024, 2024, : 162 - 172
  • [35] Semi-supervised Nuclei Segmentation Based on Consistency Regularization Constraint
    Shu J.
    Nian F.
    Lü G.
    Nian, Fudong (nianfd@hfuu.edu.cn), 1600, Science Press (33): : 643 - 652
  • [36] Semi-supervised Deep Learning via Transformation Consistency Regularization for Remote Sensing Image Semantic Segmentation
    Zhang, Bin
    Zhang, Yongjun
    Li, Yansheng
    Wan, Yi
    Guo, Haoyu
    Zheng, Zhi
    Yang, Kun
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 5782 - 5796
  • [37] Semantic Equalization Learning for Semi-Supervised SAR Building Segmentation
    Lee, Eungbean
    Jeong, Somi
    Kim, Junhee
    Sohn, Kwanghoon
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [38] Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
    Zhong, Yuanyi
    Yuan, Bodi
    Wu, Hong
    Yuan, Zhiqiang
    Peng, Jian
    Wang, Yu-Xiong
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 7253 - 7262
  • [39] A baseline for semi-supervised learning of efficient semantic segmentation models
    Grubisic, Ivan
    Orsic, Marin
    Segvic, Sinisa
    PROCEEDINGS OF 17TH INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA 2021), 2021,
  • [40] Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
    Hu, Hanzhe
    Wei, Fangyun
    Hu, Han
    Ye, Qiwei
    Cui, Jinshi
    Wang, Liwei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34