Feature-Tuning Hierarchical Transformer via token communication and sample aggregation constraint for object re-identification

IF 6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Zhi Yu , Zhiyong Huang , Mingyang Hou , Jiaming Pei , Yan Yan , Yushi Liu , Daming Sun
{"title":"Feature-Tuning Hierarchical Transformer via token communication and sample aggregation constraint for object re-identification","authors":"Zhi Yu ,&nbsp;Zhiyong Huang ,&nbsp;Mingyang Hou ,&nbsp;Jiaming Pei ,&nbsp;Yan Yan ,&nbsp;Yushi Liu ,&nbsp;Daming Sun","doi":"10.1016/j.neunet.2025.107394","DOIUrl":null,"url":null,"abstract":"<div><div>Recently, transformer-based methods have shown remarkable success in object re-identification. However, most works directly embed off-the-shelf transformer backbones for feature extraction. These methods treat all patch tokens equally, ignoring the difference of distinct patch tokens for feature representation. To solve this issue, this paper designs a feature-tuning mechanism for transformer backbones to emphasize important patches and attenuate unimportant patches. Specifically, a Feature-tuning Hierarchical Transformer (FHTrans) for object re-identification is proposed. First, we propose a plug-and-play Feature-tuning module via Token Communication (TCF) deployed within transformer encoder blocks. This module regards the class token as a pivot to achieve communication between patch tokens. Important patch tokens are emphasized, while unimportant patch tokens are attenuated, focusing more precisely on the discriminative features related to object distinction. Then, we construct a FHTrans based on the designed feature-tuning module. The encoder blocks are divided into three hierarchies considering the correlation between feature representativeness and transformer depth. As the hierarchy deepens, the communication between tokens becomes tighter. This enables the model to capture more crucial feature information. Finally, we propose a Sample Aggregation (SA) loss to impose more effective constraints on statistical characteristics among samples, thereby enhancing intra-class aggregation and guiding FHTrans to learn more discriminative features. Experiments on object re-identification benchmarks demonstrate that our method can achieve state-of-the-art performance.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"187 ","pages":"Article 107394"},"PeriodicalIF":6.0000,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0893608025002734","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Recently, transformer-based methods have shown remarkable success in object re-identification. However, most works directly embed off-the-shelf transformer backbones for feature extraction. These methods treat all patch tokens equally, ignoring the difference of distinct patch tokens for feature representation. To solve this issue, this paper designs a feature-tuning mechanism for transformer backbones to emphasize important patches and attenuate unimportant patches. Specifically, a Feature-tuning Hierarchical Transformer (FHTrans) for object re-identification is proposed. First, we propose a plug-and-play Feature-tuning module via Token Communication (TCF) deployed within transformer encoder blocks. This module regards the class token as a pivot to achieve communication between patch tokens. Important patch tokens are emphasized, while unimportant patch tokens are attenuated, focusing more precisely on the discriminative features related to object distinction. Then, we construct a FHTrans based on the designed feature-tuning module. The encoder blocks are divided into three hierarchies considering the correlation between feature representativeness and transformer depth. As the hierarchy deepens, the communication between tokens becomes tighter. This enables the model to capture more crucial feature information. Finally, we propose a Sample Aggregation (SA) loss to impose more effective constraints on statistical characteristics among samples, thereby enhancing intra-class aggregation and guiding FHTrans to learn more discriminative features. Experiments on object re-identification benchmarks demonstrate that our method can achieve state-of-the-art performance.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Neural Networks
Neural Networks 工程技术-计算机:人工智能
CiteScore
13.90
自引率
7.70%
发文量
425
审稿时长
67 days
期刊介绍: Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信