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
  • [41] Real-Time Weakly Supervised Object Detection Using Center-of-Features Localization
    Ibrahem, Hatem
    Salem, Ahmed Diefy Ahmed
    Kang, Hyun-Soo
    IEEE ACCESS, 2021, 9 : 38742 - 38756
  • [42] Weakly-supervised temporal action localization: a survey
    Baraka, AbdulRahman
    Noor, Mohd Halim Mohd
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (11) : 8479 - 8499
  • [43] Weakly-supervised temporal action localization: a survey
    AbdulRahman Baraka
    Mohd Halim Mohd Noor
    Neural Computing and Applications, 2022, 34 : 8479 - 8499
  • [44] Weakly Supervised Localization Using Deep Feature Maps
    Bency, Archith John
    Kwon, Heesung
    Lee, Hyungtae
    Karthikeyan, S.
    Manjunath, B. S.
    COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 : 714 - 731
  • [45] Simple feature pyramid network for weakly supervised object localization using multi-scale information
    Koo, Bongyeong
    Choi, Han-Soo
    Kang, Myungjoo
    MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING, 2021, 32 (04) : 1185 - 1197
  • [46] Localizing From Classification: Self-Directed Weakly Supervised Object Localization for Remote Sensing Images
    Bai, Jing
    Ren, Junjie
    Xiao, Zhu
    Chen, Zheng
    Gao, Chengxi
    Ali, Talal Ahmed Ali
    Jiao, Licheng
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (12) : 17935 - 17949
  • [47] Simple feature pyramid network for weakly supervised object localization using multi-scale information
    Bongyeong Koo
    Han-Soo Choi
    Myungjoo Kang
    Multidimensional Systems and Signal Processing, 2021, 32 : 1185 - 1197
  • [48] Object localization with electrosensory mechanism in weakly electric fish
    Miyoung Sim
    DaeEun Kim
    BMC Neuroscience, 12 (Suppl 1)
  • [49] GLNet: Global Local Network for Weakly Supervised Action Localization
    Zhang, Shiwei
    Song, Lin
    Gao, Changxin
    Sang, Nong
    IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 22 (10) : 2610 - 2622
  • [50] ACTION COHERENCE NETWORK FOR WEAKLY SUPERVISED TEMPORAL ACTION LOCALIZATION
    Zhai, Yuanhao
    Wang, Le
    Liu, Ziyi
    Zhang, Qilin
    Hua, Gang
    Zheng, Nanning
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3696 - 3700