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
Enhancing Face Recognition With Detachable Self-Supervised Bypass Networks

文献类型：期刊论文

作者He, Mingjie2,3; Zhang, Jie1,2,3; Shan, Shiguang2,3; Chen, Xilin2,3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2024
卷号33页码:1588-1599
关键词Face recognition Task analysis Three-dimensional displays Training Supervised learning Self-supervised learning Image reconstruction bypass enhanced representation learning 3D reconstruction bypass blind inpainting bypass
ISSN号1057-7149
DOI10.1109/TIP.2024.3364067
英文摘要Attributed to the development of deep networks and abundant data, automatic face recognition (FR) has quickly reached human-level capacity in the past few years. However, the FR problem is not perfectly solved in case of large poses and uncontrolled occlusions. In this paper, we propose a novel bypass enhanced representation learning (BERL) method to improve face recognition under unconstrained scenarios. The proposed method integrates self-supervised learning and supervised learning together by attaching two auxiliary bypasses, a 3D reconstruction bypass and a blind inpainting bypass, to assist robust feature learning for face recognition. Among them, the 3D reconstruction bypass enforces the face recognition network to encode pose independent 3D facial information, which enhances the robustness to various poses. The blind inpainting bypass enforces the face recognition network to capture more facial context information for face inpainting, which enhances the robustness to occlusions. The whole framework is trained in end-to-end manner with two self-supervised tasks above and the classic supervised face identification task. During inference, the two auxiliary bypasses can be detached from the face recognition network, avoiding any additional computational overhead. Extensive experimental results on various face recognition benchmarks show that, without any cost of extra annotations and computations, our method outperforms state-of-the-art methods. Moreover, the learnt representations can also well generalize to other face-related downstream tasks such as the facial attribute recognition with limited labeled data.
资助项目National Key Research and Development Program of China
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001177650300003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/38724]  
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, Inst Intelligent Comp Technol, Suzhou 215000, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc Chinese Acad Sci, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 He, Mingjie,Zhang, Jie,Shan, Shiguang,et al. Enhancing Face Recognition With Detachable Self-Supervised Bypass Networks[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:1588-1599.
APA He, Mingjie,Zhang, Jie,Shan, Shiguang,&Chen, Xilin.(2024).Enhancing Face Recognition With Detachable Self-Supervised Bypass Networks.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,1588-1599.
MLA He, Mingjie,et al."Enhancing Face Recognition With Detachable Self-Supervised Bypass Networks".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):1588-1599.

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。