Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions
文献类型：期刊论文
| 作者 | Ren, Min4 ; Wang, Yunlong3; Zhu, Yuhao2; Zhang, Kunbo3; Sun, Zhenan1,3
|
| 刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
 |
| 出版日期 | 2023-12-01 |
| 卷号 | 45期号:12页码:15120-15136 |
| ISSN号 | 0162-8828 |
| 关键词 | Biometrics deep learning face recognition graph neural networks iris recognition |
| DOI | 10.1109/TPAMI.2023.3298836 |
| 通讯作者 | Sun, Zhenan(znsun@nlpr.ia.ac.cn) |
| 英文摘要 | Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods. |
| 资助项目 | National Key Research and Development Program of China[2022YFC3310400] ; National Natural Science Foundation of China[62276025] ; National Natural Science Foundation of China[62276263] ; National Natural Science Foundation of China[62006225] ; National Natural Science Foundation of China[62071468] ; Shenzhen Technology Plan Program[KQTD20170331093217368] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | IEEE COMPUTER SOC |
| WOS记录号 | WOS:001130146400066 |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Shenzhen Technology Plan Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55533]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Sun, Zhenan |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 2.China Acad Railway Sci, Postgrad Dept, Beijing 100081, Peoples R China 3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ren, Min,Wang, Yunlong,Zhu, Yuhao,et al. Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15120-15136. |
| APA | Ren, Min,Wang, Yunlong,Zhu, Yuhao,Zhang, Kunbo,&Sun, Zhenan.(2023).Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15120-15136. |
| MLA | Ren, Min,et al."Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15120-15136. |
入库方式： OAI收割
来源：自动化研究所
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。