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
  • [31] Generative Prompt Model for Weakly Supervised Object Localization
    Zhao, Yuzhong
    Ye, Qixiang
    Wu, Weijia
    Shen, Chunhua
    Wan, Fang
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 6328 - 6338
  • [32] Soft Proposal Networks for Weakly Supervised Object Localization
    Zhu, Yi
    Zhou, Yanzhao
    Ye, Qixiang
    Qiu, Qiang
    Jiao, Jianbin
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1859 - 1868
  • [33] Adaptive Zone Learning for Weakly Supervised Object Localization
    Chen, Zhiwei
    Wang, Siwei
    Cao, Liujuan
    Shen, Yunhang
    Ji, Rongrong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 14
  • [34] Video-based Object Recognition with Weakly Supervised Object Localization
    Liu, Yang
    Kouskouridas, Rigas
    Kim, Tae-Kyun
    Proceedings 3rd IAPR Asian Conference on Pattern Recognition ACPR 2015, 2015, : 46 - 50
  • [35] Exploring Intrinsic Discrimination and Consistency for Weakly Supervised Object Localization
    Wang, Changwei
    Xu, Rongtao
    Xu, Shibiao
    Meng, Weiliang
    Wang, Ruisheng
    Zhang, Xiaopeng
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 1045 - 1058
  • [36] Spatial-Aware Token for Weakly Supervised Object Localization
    Wu, Pingyu
    Zhai, Wei
    Cao, Yang
    Luo, Jiebo
    Zha, Zheng-Jun
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 1844 - 1854
  • [37] Combinational Class Activation Maps for Weakly Supervised Object Localization
    Yang, Seunghan
    Kim, Yoonhyung
    Kim, Youngeun
    Kim, Changick
    2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 2930 - 2938
  • [38] Two-Phase Learning for Weakly Supervised Object Localization
    Kim, Dahun
    Cho, Donghyeon
    Yoo, Donggeun
    Kweon, In So
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 3554 - 3563
  • [39] Weakly-supervised object localization in unlabeled image collection
    Qu, Yanyun
    Liu, Han
    Yang, Xiaoqing
    Fang, Suwen
    Wang, Hanzi
    MULTIMEDIA SYSTEMS, 2013, 19 (01) : 51 - 63
  • [40] Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
    Wenju Xu
    Yuanwei Wu
    Wenchi Ma
    Guanghui Wang
    Neural Processing Letters, 2020, 51 : 993 - 1006