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
下载
收藏
页码:9958 / 9968
页数:11
相关论文
共 50 条
  • [11] Semi-Supervised Semantic Segmentation With Region Relevance
    Chen, Rui
    Chen, Tao
    Wang, Qiong
    Yao, Yazhou
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 852 - 857
  • [12] A semi-supervised approach for the semantic segmentation of trajectories
    Soares Junior, Amilcar
    Times, Valeria Cesario
    Renso, Chiara
    Matwin, Stan
    Cabral, Lucidio A. F.
    2018 19TH IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2018), 2018, : 145 - 154
  • [13] Revisiting Consistency for Semi-Supervised Semantic Segmentation
    Grubisic, Ivan
    Orsic, Marin
    Segvic, Sinisa
    SENSORS, 2023, 23 (02)
  • [14] Information Transfer in Semi-Supervised Semantic Segmentation
    Wu, Jiawei
    Fan, Haoyi
    Li, Zuoyong
    Liu, Guang-Hai
    Lin, Shouying
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (02) : 1174 - 1185
  • [15] Alleviating Class Imbalance in Semi-Supervised Multi-Organ Segmentation via Balanced Subclass Regularization
    Feng, Zhenghao
    Wen, Lu
    Yan, Binyu
    Cui, Jiaqi
    Wang, Yan
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 2450 - 2454
  • [16] Mutual information deep regularization for semi-supervised segmentation
    Peng, Jizong
    Pedersoli, Marco
    Desrosiers, Christian
    MEDICAL IMAGING WITH DEEP LEARNING, VOL 121, 2020, 121 : 601 - 613
  • [17] Neuron Segmentation based on CNN with Semi-supervised Regularization
    Xu, Kun
    Su, Hang
    Zhu, Jun
    Guan, Ji-Song
    Zhang, Bo
    PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), 2016, : 1324 - 1332
  • [18] Multi-Dimensional Manifolds Consistency Regularization for semi-supervised remote sensing semantic segmentation
    Lu, Yujie
    Zhang, Yongjun
    Cui, Zhongwei
    Long, Wei
    Chen, Ziyang
    KNOWLEDGE-BASED SYSTEMS, 2024, 299
  • [19] A Residual Correction Approach for Semi-supervised Semantic Segmentation
    Li, Haoliang
    Zheng, Huicheng
    PATTERN RECOGNITION AND COMPUTER VISION, PT IV, 2021, 13022 : 90 - 102
  • [20] ROBUST ADVERSARIAL LEARNING FOR SEMI-SUPERVISED SEMANTIC SEGMENTATION
    Zhang, Jia
    Li, Zhixin
    Zhang, Canlong
    Ma, Huifang
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 728 - 732