中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization

文献类型：期刊论文

作者Chen, Dong4; Pan, Xingjia3; Tang, Fan2; Dong, Weiming1; Xu, Changsheng1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2023
卷号32页码:5779-5793
关键词High-order self-correlation class activation map structure preservation weakly supervised object localization
ISSN号1057-7149
DOI10.1109/TIP.2023.3323793
英文摘要By exploring the localizable representations in deep CNN, weakly supervised object localization (WSOL) methods could determine the position of the object in each image just trained by the classification task. However, the partial activation problem caused by the discriminant function makes the network unable to locate objects accurately. To alleviate this problem, we propose Structure-Preserved Attention Activated Network (SPA(2)Net), a simple and effective one-stage WSOL framework to explore the ability of structure preservation of deep features. Different from traditional WSOL approaches, we decouple the object localization task from the classification branch to reduce their mutual influence by involving a localization branch which is online refined by a self-supervised structural-preserved localization mask. Specifically, we employ the high-order self-correlation as structural prior to enhance the perception of spatial interaction within convolutional features. By succinctly combining the structural prior with spatial attention, activations by SPA(2)Net will spread from part to the whole object during training. To avoid the structure-missing issue caused by the classification network, we furthermore utilize the restricted activation loss (RAL) to distinguish the difference between foreground and background in the channel dimension. In conjunction with the self-supervised localization branch, SPA(2)Net can directly predict the class-irrelevant localization map while prompting the network to pay more attention to the target region for accurate localization. Extensive experiments on two publicly available benchmarks, including CUB-200-2011 and ILSVRC, show that our SPA(2)Net achieves substantial and consistent performance gains compared with baseline approaches. The code and models are available at https://github.com/MsterDC/SPA2Net.
资助项目National Natural Science Foundation of China[62102162] ; National Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[61832002] ; Beijing Natural Science Foundation[L221013]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001104979200002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/38071]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Tang, Fan
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
3.Momenta, Beijing 100018, Peoples R China
4.Jilin Univ, Sch Artificial Intelligence, Changchun 130012, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Dong,Pan, Xingjia,Tang, Fan,et al. SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:5779-5793.
APA Chen, Dong,Pan, Xingjia,Tang, Fan,Dong, Weiming,&Xu, Changsheng.(2023).SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,5779-5793.
MLA Chen, Dong,et al."SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):5779-5793.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。