AAformer: Auto-Aligned Transformer for Person Re-Identification

doi:10.1109/TNNLS.2023.3301856

CASIA OpenIR > 紫东太初大模型研究中心

	AAformer: Auto-Aligned Transformer for Person Re-Identification
	Zhu, Kuan1 ; Guo, Haiyun1,2,3 ; Zhang, Shiliang 4; Wang, Yaowei 5; Liu, Jing1,2 ; Wang, Jinqiao1,2,6,7 ; Tang, Ming1
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2023-08-25
页码	11
通讯作者	Guo, Haiyun(haiyun.guo@nlpr.ia.ac.cn)
摘要	In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely on pretrained human parsing models and fail in locating the identifiable nonhuman parts (e.g., knapsack). In this article, we introduce an alignment scheme in transformer architecture for the first time and propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level. We introduce the "Part tokens (PARTs)", which are learnable vectors, to extract part features in the transformer. A PART only interacts with a local subset of patches in self-attention and learns to be the part representation. To adaptively group the image patches into different subsets, we design the auto-alignment. Auto-alignment employs a fast variant of optimal transport (OT) algorithm to online cluster the patch embeddings into several groups with the PARTs as their prototypes. AAformer integrates the part alignment into the self-attention and the output PARTs can be directly used as part features for retrieval. Extensive experiments validate the effectiveness of PARTs and the superiority of AAformer over various state-of-the-art methods.
关键词	Auto-alignment part-level representation person re-identification (re-ID) transformer
DOI	10.1109/TNNLS.2023.3301856
关键词[WOS]	NETWORK
收录类别	SCI
语种	英语
资助项目	Key-Area Research and Development Program of Guangdong Province[2021B0101410003] ; National Natural Science Foundation of China[62276260] ; National Natural Science Foundation of China[62002356] ; National Natural Science Foundation of China[61976210]
项目资助者	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001060547200001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：9[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53198
专题	紫东太初大模型研究中心
通讯作者	Guo, Haiyun
作者单位	1.Chinese Acad Sci, Inst Automat, Fdn Model Res Ctr, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Dev Res Inst Guangzhou Smart City, Guangzhou 510805, Peoples R China 4.Peking Univ, Sch Comp Sci, Natl Key Lab Multimedia Informat Proc, Beijing 100871, Peoples R China 5.Peng Cheng Lab, Shenzhen 518066, Peoples R China 6.Wuhan AI Res, Wuhan 430073, Peoples R China 7.Peng Cheng Lab, Shenzhen 518066, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhu, Kuan,Guo, Haiyun,Zhang, Shiliang,et al. AAformer: Auto-Aligned Transformer for Person Re-Identification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:11.
APA	Zhu, Kuan.,Guo, Haiyun.,Zhang, Shiliang.,Wang, Yaowei.,Liu, Jing.,...&Tang, Ming.(2023).AAformer: Auto-Aligned Transformer for Person Re-Identification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,11.
MLA	Zhu, Kuan,et al."AAformer: Auto-Aligned Transformer for Person Re-Identification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):11.