Acknowledging the Unknown for Multi-label Learning with Single Positive Labels

被引:4
|
作者
Zhou, Donghao [1 ,2 ]
Chen, Pengfei [3 ]
Wang, Qiong [1 ]
Chen, Guangyong [4 ]
Heng, Pheng-Ann [1 ,5 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Guangdong Prov Key Lab Comp Vis & Virtual Real Te, Shenzhen, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
[3] Tencent Technol, Shenzhen, Peoples R China
[4] Zhejiang Lab, Hangzhou, Peoples R China
[5] Chinese Univ Hong Kong, Hong Kong, Peoples R China
来源
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
Weakly supervised learning; Single positive multi-label learning; Entropy maximization; Pseudo-labeling;
D O I
10.1007/978-3-031-20053-3_25
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are assumed as negative labels in SPML, which introduces false negative labels and causes model training to be dominated by assumed negative labels. In this work, we choose to treat all unannotated labels from an alternative perspective, i.e. acknowledging they are unknown. Hence, we propose entropy-maximization (EM) loss to attain a special gradient regime for providing proper supervision signals. Moreover, we propose asymmetric pseudo-labeling (APL), which adopts asymmetric-tolerance strategies and a self-paced procedure, to cooperate with EM loss and then provide more precise supervision. Experiments show that our method significantly improves performance and achieves state-of-the-art results on all four benchmarks. Code is available at https://github.com/Correr-Zhou/SPML-AckTheUnknown.
引用
收藏
页码:423 / 440
页数:18
相关论文
共 50 条
  • [31] Discriminatory Label-specific Weights for Multi-label Learning with Missing Labels
    Rastogi, Reshma
    Kumar, Sanjay
    [J]. NEURAL PROCESSING LETTERS, 2023, 55 (02) : 1397 - 1431
  • [32] Global and Adaptive Local Label Correlation for Multi-label Learning with Missing Labels
    Jiang, Qingxia
    Li, Peipei
    Zhang, Yuhong
    Hu, Xuegang
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [33] Low rank label subspace transformation for multi-label learning with missing labels
    Kumar, Sanjay
    Rastogi, Reshma
    [J]. INFORMATION SCIENCES, 2022, 596 : 53 - 72
  • [34] Discriminatory Label-specific Weights for Multi-label Learning with Missing Labels
    Reshma Rastogi
    Sanjay Kumar
    [J]. Neural Processing Letters, 2023, 55 : 1397 - 1431
  • [35] Learning Label-Specific Features for Multi-Label Classification with Missing Labels
    Huang, Jun
    Qin, Feng
    Zheng, Xiao
    Cheng, Zekai
    Yuan, Zhixiang
    Zhang, Weigang
    [J]. 2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2018,
  • [36] Attribute reduction for multi-label classification based on labels of positive region
    Fan, Xiaodong
    Chen, Qi
    Qiao, Zhijun
    Wang, Changzhong
    Ten, Mingyan
    [J]. SOFT COMPUTING, 2020, 24 (18) : 14039 - 14049
  • [37] Attribute reduction for multi-label classification based on labels of positive region
    Xiaodong Fan
    Qi Chen
    Zhijun Qiao
    Changzhong Wang
    Mingyan Ten
    [J]. Soft Computing, 2020, 24 : 14039 - 14049
  • [38] Prompt Expending for Single Positive Multi-Label Learning with Global Unannotated Categories
    Li, Zhongnian
    Ying, Peng
    Wei, Meng
    Sun, Tongfeng
    Xu, Xinzheng
    [J]. PROCEEDINGS OF THE 4TH ANNUAL ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2024, 2024, : 561 - 569
  • [39] Discover Multiple Novel Labels in Multi-Instance Multi-Label Learning
    Zhu, Yue
    Ting, Kai Ming
    Zhou, Zhi-Hua
    [J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2977 - 2983
  • [40] Multi-label classification with Missing Labels using Label Correlation and Robust Structural Learning
    Rastogi, Reshma
    Mortaza, Sayed
    [J]. KNOWLEDGE-BASED SYSTEMS, 2021, 229