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
基金
中国国家自然科学基金; 新加坡国家研究基金会;
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
下载
收藏
页码:5484 / 5494
页数:11
相关论文
共 50 条
  • [21] Feature disparity learning for weakly supervised object localization
    Li, Bingfeng
    Ruan, Haohao
    Li, Xinwei
    Wang, Keping
    IMAGE AND VISION COMPUTING, 2024, 145
  • [22] Background Activation Suppression for Weakly Supervised Object Localization
    Wu, Pingyu
    Zhai, Wei
    Cao, Yang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 14228 - 14237
  • [23] Strengthen Learning Tolerance for Weakly Supervised Object Localization
    Guo, Guangyu
    Han, Junwei
    Wan, Fang
    Zhang, Dingwen
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 7399 - 7408
  • [24] Weakly Supervised Object Localization with Progressive Domain Adaptation
    Su, Shuochen
    Heide, Felix
    Swanson, Robin
    Klein, Jonathan
    Callenberg, Clara
    Hullin, Matthias
    Heidrich, Wolfgang
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : CP40 - CP40
  • [25] DANet: Divergent Activation for Weakly Supervised Object Localization
    Xue, Haolan
    Liu, Chang
    Wan, Fang
    Jiao, Jianbin
    Ji, Xiangyang
    Ye, Qixiang
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6588 - 6597
  • [26] Shallow Feature Matters for Weakly Supervised Object Localization
    Wei, Jun
    Wang, Qin
    Li, Zhen
    Wang, Sheng
    Zhou, S. Kevin
    Cui, Shuguang
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 5989 - 5997
  • [27] ViTOL: Vision Transformer for Weakly Supervised Object Localization
    Gupta, Saurav
    Lakhotia, Sourav
    Rawat, Abhay
    Tallamraju, Rahul
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 4100 - 4109
  • [28] Weakly Supervised Object Localization Using Size Estimates
    Shi, Miaojing
    Ferrari, Vittorio
    COMPUTER VISION - ECCV 2016, PT V, 2016, 9909 : 105 - 121
  • [29] Hierarchical complementary learning for weakly supervised object localization
    Benassou, Sabrina Narimene
    Shi, Wuzhen
    Jiang, Feng
    Benzine, Abdallah
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2022, 100
  • [30] Adversarial Complementary Learning for Weakly Supervised Object Localization
    Zhang, Xiaolin
    Wei, Yunchao
    Feng, Jiashi
    Yang, Yi
    Huang, Thomas
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 1325 - 1334