Rethinking the Localization in Weakly Supervised Object Localization

被引:2
|
作者
Xu, Rui [1 ]
Luo, Yong [2 ,3 ]
Hu, Han [4 ]
Du, Bo [2 ,3 ]
Shen, Jialie [5 ]
Wen, Yonggang [6 ]
机构
[1] Wuhan Univ, Sch Comp Sci, Wuhan, Peoples R China
[2] Wuhan Univ, Wuhan, Peoples R China
[3] Hubei Luojia Lab, Wuhan, Peoples R China
[4] Beijing Inst Technol, Beijing, Peoples R China
[5] City Univ London, London, England
[6] Nanyang Technol Univ, Singapore, Singapore
来源
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023 | 2023年
基金
新加坡国家研究基金会; 中国国家自然科学基金;
关键词
weakly supervised; object localization; binary-class detector; weighted entropy; noisy label;
D O I
10.1145/3581783.3611959
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision. This task is to localize the objects in the images given only the image-level supervision. Recently, dividing WSOL into two parts (class-agnostic object localization and object classification) has become the state-of-the-art pipeline for this task. However, existing solutions under this pipeline usually suffer from the following drawbacks: 1) they are not flexible since they can only localize one object for each image due to the adopted single-class regression (SCR) for localization; 2) the generated pseudo bounding boxes may be noisy, but the negative impact of such noise is not well addressed. To remedy these drawbacks, we first propose to replace SCR with a binary-class detector (BCD) for localizing multiple objects, where the detector is trained by discriminating the foreground and background. Then we design a weighted entropy (WE) loss using the unlabeled data to reduce the negative impact of noisy bounding boxes. Extensive experiments on the popular CUB-200-2011 and ImageNet-1K datasets demonstrate the effectiveness of our method.
引用
收藏
页码:5484 / 5494
页数:11
相关论文
共 50 条
  • [31] NAD: Neuron Activation based Divergence Maps for Weakly Supervised Object Localization
    Bagga, Siddhant
    Gupta, Sarthak
    Bhatia, Mohinder Pal Singh
    Dhurandher, Sanjay Kumar
    Goyal, Anish
    2020 INTERNATIONAL CONFERENCE ON EMERGING SMART COMPUTING AND INFORMATICS (ESCI), 2020, : 60 - 64
  • [32] Learning Consistency From High-Confidence Pseudo-Labels for Weakly Supervised Object Localization
    Sun, Kangbo
    Zhu, Jie
    IEEE ACCESS, 2023, 11 : 16657 - 16666
  • [33] Hierarchical saliency mapping for weakly supervised object localization based on class activation mapping
    Cheng, Zhuo
    Li, Hongjian
    Zeng, Xiangyan
    Wang, Meiqi
    Duan, Xiaolin
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (41-42) : 31283 - 31298
  • [34] Weakly Supervised Object Localization Using Self-Paced Pyramid Adversarial Learning
    Pan, FuCheng
    Bian, BeiLei
    Wang, BinXu
    Yang, YuePing
    Ju, XiaoMing
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [35] Hierarchical saliency mapping for weakly supervised object localization based on class activation mapping
    Zhuo Cheng
    Hongjian Li
    Xiangyan Zeng
    Meiqi Wang
    Xiaolin Duan
    Multimedia Tools and Applications, 2020, 79 : 31283 - 31298
  • [36] Latent SVM for Object Localization in Weakly Labeled Videos
    Rochan, Mrigank
    Wang, Yang
    2015 12TH CONFERENCE ON COMPUTER AND ROBOT VISION CRV 2015, 2015, : 200 - 207
  • [37] Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
    Lee, Jungbeom
    Kim, Eunji
    Mok, Jisoo
    Yoon, Sungroh
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1618 - 1634
  • [38] Large-Scale Weakly Supervised Object Localization via Latent Category Learning
    Wang, Chong
    Huang, Kaiqi
    Ren, Weiqiang
    Zhang, Junge
    Maybank, Steve
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (04) : 1371 - 1385
  • [39] Weakly-supervised video object localization with attentive spatio-temporal correlation
    Wang, Mingui
    Cui, Di
    Wu, Lifang
    Jian, Meng
    Chen, Yukun
    Wang, Dong
    Liu, Xu
    PATTERN RECOGNITION LETTERS, 2021, 145 : 232 - 239
  • [40] Temporal Dropout for Weakly Supervised Action Localization
    Xie, Chi
    Zhuang, Zikun
    Zhao, Shengjie
    Liang, Shuang
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (03)