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
Locality-Aware Channel-Wise Dropout for Occluded Face Recognition

文献类型：期刊论文

作者He, Mingjie1,2; Zhang, Jie1,2; Shan, Shiguang1,2,3,4; Liu, Xiao5; Wu, Zhongqin5; Chen, Xilin1,2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:788-798
关键词Face recognition Feature extraction Liquid crystal displays Robustness Neurons Image reconstruction Dictionaries Occluded face recognition locality-aware channel-wise dropout spatial attention module
ISSN号1057-7149
DOI10.1109/TIP.2021.3132827
英文摘要Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as a useful approach. However, these artificial occlusions are commonly generated by adding a black rectangle or several object templates including sunglasses, scarfs and phones, which cannot well simulate the realistic occlusions. In this paper, based on the argument that the occlusion essentially damages a group of neurons, we propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Specifically, we first employ a spatial regularization to encourage each feature channel to respond to local and different face regions. Then, the locality-aware channel-wise dropout (LCD) is designed to simulate occlusions by dropping out a few feature channels. The proposed LCD can encourage its succeeding layers to minimize the intra-class feature variance caused by occlusions, thus leading to improved robustness against occlusion. In addition, we design an auxiliary spatial attention module by learning a channel-wise attention vector to reweight the feature channels, which improves the contributions of non-occluded regions. Extensive experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.
资助项目National Key Research and Development Program of China[2017YFA0700800] ; National Natural Science Foundation of China[61806188] ; National Natural Science Foundation of China[61976219] ; Shanghai Municipal Science and Technology Major Project[2017SHZDZX01]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000739998500001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/18371]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Shan, Shiguang
作者单位1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
4.Peng Cheng Lab, Shenzhen 518055, Peoples R China
5.Tomorrow Adv Life Educ Grp TAL, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714		 He, Mingjie,Zhang, Jie,Shan, Shiguang,et al. Locality-Aware Channel-Wise Dropout for Occluded Face Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:788-798.
APA He, Mingjie,Zhang, Jie,Shan, Shiguang,Liu, Xiao,Wu, Zhongqin,&Chen, Xilin.(2022).Locality-Aware Channel-Wise Dropout for Occluded Face Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,788-798.
MLA He, Mingjie,et al."Locality-Aware Channel-Wise Dropout for Occluded Face Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):788-798.

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。