CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification
文献类型:会议论文
作者 | Fu, Chaoyou2,3; Hu, Yibo1; Wu, Xiang2; Shi, Hailin1; Mei, Tao1; He, Ran2,3 |
出版日期 | 2021 |
会议日期 | 2021.10.11 |
会议地点 | 线上 |
英文摘要 | Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment. In order to mitigate the impact of large modality discrepancy, existing works manually design various two-stream architectures to separately learn modality-specific and modality-sharable representations. Such a manual design routine, however, highly depends on massive experiments and empirical practice, which is time consuming and labor intensive. In this paper, we systematically study the manually designed architectures, and identify that appropriately separating Batch Normalization (BN) layers is the key to bring a great boost towards cross-modality matching. Based on this observation, the essential objective is to find the optimal separation scheme for each BN layer. To this end, we propose a novel method, named Cross-Modality Neural Architecture Search (CM- NAS). It consists of a BN-oriented search space in which the standard optimization can be fulfilled subject to the cross-modality task. Equipped with the searched architecture, our method outperforms state-of-the-art counterparts in both two benchmarks, improving the Rank-1/mAP by 6.70%/6.13% on SYSU-MM01 and by 12.17%/11.23% on RegDB. Code is released at https://github.com/ JDAI-CV/CM-NAS. |
源URL | [http://ir.ia.ac.cn/handle/173211/48689] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | He, Ran |
作者单位 | 1.JD AI Research 2.NLPR & CEBSIT & CRIPAC, CASIA 3.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Fu, Chaoyou,Hu, Yibo,Wu, Xiang,et al. CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification[C]. 见:. 线上. 2021.10.11. |
入库方式: OAI收割
来源:自动化研究所
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。