research-article

Improving Federated Person Re-Identification through Feature-Aware Proximity and Aggregation

Authors:

Pengling Zhang,

Shuoyao WangAuthors Info & Claims

MM '23: Proceedings of the 31st ACM International Conference on Multimedia

Pages 2498 - 2506

https://doi.org/10.1145/3581783.3612350

Published: 27 October 2023 Publication History

Abstract

Person re-identification (ReID) is a challenging task that aims to identify individuals across multiple non-overlapping camera views. To enhance the performance and robustness of ReID models, it is crucial to train them over multiple data sources. However, the traditional centralized approach poses a significant challenge to privacy as it requires collecting data from distributed data owners. To overcome this challenge, we employ the federated learning approach, which enables distributed model training without compromising data privacy. In this paper, we propose a novel feature-aware local proximity and global aggregation method for federated ReID to extract robust feature representations. Specifically, we introduce a proximal term and a feature regularization term for local model training to improve local training accuracy while ensuring global aggregation convergence. Furthermore, we use the cosine distance of backbone features to determine the global aggregation weight of each local model. Our proposed method significantly improves the performance and generalization of the global model. Extensive experiments demonstrate the effectiveness of our proposal. Specifically, our method achieves an additional 27.3% Rank-1 average accuracy in federated full supervision and an extra 20.3% mean Average Precision (mAP) on DukeMTMC in federated domain generalization.

References

[1]

Taiqing Wang, Shaogang Gong, Xiatian Zhu, and Shengjin Wang. Person re-identification by video ranking. In ECCV, pages 688--703, 2014.

[2]

Davide Baltieri, Roberto Vezzani, and Rita Cucchiara. 3dpes: 3d people dataset for surveillance and forensics. In ACM workshop Human gesture and behavior understanding, pages 59--64, 2011.

[3]

Zhedong Zheng, Liang Zheng, and Yi Yang. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In ICCV, pages 3754--3762, 2017.

[4]

Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. Scalable person re-identification: A benchmark. In ICCV, pages 1116--1124, 2015.

Digital Library

[5]

Jianqing Zhu, Huanqiang Zeng, Shengcai Liao, Zhen Lei, Canhui Cai, and Lixin Zheng. Deep hybrid similarity learning for person re-identification. In IEEE TCSVT, 28(11):3183--3193, 2018.

[6]

Hongchen Tan, Xiuping Liu, Yuhao Bian, Huasheng Wang, and Baocai Yin. Incomplete descriptor mining with elastic loss for person re-identification. In IEEE TCSVT, 32(1):160--171, 2022.

[7]

Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang. Transreid: Transformer-based object re-identification. In ICCV, pages 15013--15022, 2021.

[8]

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, and Tao Xiang. Learning to generate novel domains for domain generalization. In ECCV, pages 561--578, 2020.

Digital Library

[9]

Zijie Zhuang, Longhui Wei, Lingxi Xie, Tianyu Zhang, Hengheng Zhang, Haozhe Wu, Haizhou Ai, and Qi Tian. Rethinking the distribution gap of person re-identification with camera-based batch normalization. In ECCV, pages 140--157, 2020.

Digital Library

[10]

Jianzhu Guo, Xiangyu Zhu, Chenxu Zhao, Dong Cao, Zhen Lei, and Stan Z Li. Learning meta face recognition in unseen domains. In CVPR, pages 6163--6172, 2020.

[11]

Seokeon Choi, Taekyung Kim, Minki Jeong, Hyoungseob Park, and Changick Kim. Meta batch-instance normalization for generalizable person re-identification. In CVPR, pages 3425--3435, June 2021.

[12]

Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, and Ling-Yu Duan. Generalizable person re-identification with relevance-aware mixture of experts. In CVPR, pages 16145--16154, 2021.

[13]

Zhong Zhang, Yanan Wang, Shuang Liu, Baihua Xiao, and Tariq S. Durrani. Cross-domain person re-identification using heterogeneous convolutional network. In IEEE TCSVT, 32(3):1160--1171, 2022.

[14]

Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. Communication-efficient learning of deep networks from decentralized data. In AISTATS, pages 1273--1282, 2017.

[15]

Quande Liu, Cheng Chen, Jing Qin, Qi Dou, and Pheng-Ann Heng. Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space. In CVPR, pages 1013--1023, 2021.

[16]

Tehrim Yoon, Sumin Shin, Sung Ju Hwang, and Eunho Yang. Fedmix: Approximation of mixup under mean augmented federated learning. In arXiv preprint arXiv:2107.00233, 2021.

[17]

Qinbin Li, Bingsheng He, and Dawn Song. Model-contrastive federated learning. In CVPR, pages 10713--10722, 2021.

[18]

Weiming Zhuang, Yonggang Wen, Xuesen Zhang, Xin Gan, Daiying Yin, Dongzhan Zhou, Shuai Zhang, and Shuai Yi. Performance optimization of federated person re-identification via benchmark analysis. In ACM MM, pages 955--963, 2020.

Digital Library

[19]

Anit Kumar Sahu, Tian Li, Maziar Sanjabi, Manzil Zaheer, Ameet Talwalkar, and Virginia Smith. On the convergence of federated optimization in heterogeneous networks. In arXiv preprint arXiv:1812.06127, 2018.

[20]

Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia, Feifei Wang, Ehsan Adeli, Li Fei-Fei, and Daniel Rubin. Rethinking architecture design for tackling data heterogeneity in federated learning. In CVPR, pages 10061--10071, 2022.

[21]

Hao Luo, Wei Jiang, Xuan Zhang, Xing Fan, Jingjing Qian, and Chi Zhang. Alignedreid: Dynamically matching local information for person re-identification. In Pattern Recognition, 94:53--61, 2019.

Digital Library

[22]

Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, and Zhangyang Wang. Abd-net: Attentive but diverse person re-identification. In ICCV, pages 8351--8361, 2019.

[23]

Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, and Xi Zhou. Learning discriminative features with multiple granularities for person re-identification. In ACM MM, pages 274--282, 2018.

Digital Library

[24]

Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, and Shengjin Wang. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In ECCV, pages 480--496, 2018.

Digital Library

[25]

Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, and Wei Shi. Pose-guided feature disentangling for occluded person re-identification based on transformer. In AAAI, pages 2540--2549, 2022.

[26]

Guowen Zhang, Pingping Zhang, Jinqing Qi, and Huchuan Lu. Hat: Hierarchical aggregation transformers for person re-identification. In ACM MM, pages 516--525, 2021.

Digital Library

[27]

Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. Unsupervised person re-identification: Clustering and fine-tuning. In TOMM, 14(4), oct 2018.

Digital Library

[28]

Yixiao Ge, Dapeng Chen, and Hongsheng Li. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In ICLR, 2019.

[29]

Chenyang Zhang, Yongqiang Tang, Zhizhong Zhang, Ding Li, Xuebing Yang, and Wensheng Zhang. Improving domain-adaptive person re-identification by dual-alignment learning with camera-aware image generation. In IEEE TCSVT, 31(11):4334--4346, 2021.

[30]

Shihua Li, Mingkuan Yuan, Jie Chen, and Zhilan Hu. Adadc: Adaptive deep clustering for unsupervised domain adaptation in person re-identification. In IEEE TCSVT, 32(6):3825--3838, 2022.

[31]

Devinder Kumar, Parthipan Siva, Paul Marchwica, and Alexander Wong. Unsupervised domain adaptation in person re-id via k-reciprocal clustering and large-scale heterogeneous environment synthesis. In WACV, pages 2645--2654, 2020.

[32]

Yuan Liang, Yange Guo, Yanxia Gong, Chunjie Luo, Jianfeng Zhan, and Yunyou Huang. An isolated data island benchmark suite for federated learning. arXiv preprint arXiv:2008.07257, 2020.

[33]

Bing Luo, Wenli Xiao, Shiqiang Wang, Jianwei Huang, and Leandros Tassiulas. Tackling system and statistical heterogeneity for federated learning with adaptive client sampling. In IEEE INFOCOM 2022, pages 1739--1748, 2022.

Digital Library

[34]

Weiming Zhuang, Xin Gan, Yonggang Wen, and Shuai Zhang. Optimizing performance of federated person re-identification: Benchmarking and analysis. In TOMM, 19(1s):1--18, 2023.

Digital Library

[35]

Guile Wu and Shaogang Gong. Decentralised learning from independent multi-domain labels for person re-identification. In AAAI, volume 35, pages 2898--2906, 2021.

[36]

Wei Li, Rui Zhao, and Xiaogang Wang. Human reidentification with transferred metric learning. In ACCV, pages 31--44, 2012.

Digital Library

[37]

Longhui Wei, Shiliang Zhang, Wen Gao, and Qi Tian. Person transfer gan to bridge domain gap for person re-identification. In CVPR, pages 79--88, 2018.

[38]

Zhilu Zhang and Mert Sabuncu. Generalized cross entropy loss for training deep neural networks with noisy labels. In NeurlIPS, volume 31, 2018.

[39]

Alexander Hermans, Lucas Beyer, and Bastian Leibe. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.

[40]

Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. Deepreid: Deep filter pairing neural network for person re-identification. In ICCV, pages 152--159, 2014.

Digital Library

[41]

Douglas Gray and Hai Tao. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In ECCV, pages 262--275, 2008.

Digital Library

[42]

Martin Hirzer, Csaba Beleznai, Peter M Roth, and Horst Bischof. Person re-identification by descriptive and discriminative classification. In SCIA, pages 91--102, 2011.

[43]

Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. In JMLR, 9(86):2579--2605, 2008

Cited By

Wu XLiu XNiu JWang HTang SZhu GSu HCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank DecompositionProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681588(7172-7181)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681588
Ling TShi SWang HHu CWang DCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Federated Morozov Regularization for Shortcut Learning in Privacy Preserving Learning with Watermarked Image DataProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681480(4899-4908)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681480
Jia RXie WLei JLi YCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Adaptive Hierarchical Aggregation for Federated Object DetectionProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681158(3732-3740)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681158
Show More Cited By

Index Terms

Improving Federated Person Re-Identification through Feature-Aware Proximity and Aggregation
1. Information systems
  1. Information retrieval

Recommendations

Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
MM '21: Proceedings of the 29th ACM International Conference on Multimedia

Person re-identification (ReID) aims to re-identify a person from non-overlapping camera views. Since person ReID data contains sensitive personal information, researchers have adopted federated learning, an emerging distributed training method, to ...
Enhancing Person Re-identification in a Self-Trained Subspace

Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms ...
Camera-aware progressive learning for unsupervised person re-identification
Abstract
Unsupervised person re-identification (Re-ID) is a challenging task due to the problems of the view-specific gap across different cameras and the missing of ground truth labels. The intra-class variance caused by the camera domain gap makes the ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '23: Proceedings of the 31st ACM International Conference on Multimedia

October 2023

9913 pages

ISBN:9798400701085

DOI:10.1145/3581783

General Chairs:
Abdulmotaleb El Saddik
University of Ottawa, Canada & MBZUAI, UAE
,
Tao Mei
HiDream.ai, China
,
Rita Cucchiara
University of Modena and Reggio Emilia, Italy
,
Program Chairs:
Marco Bertini
University of Florence, Italy
,
Diana Patricia Tobon Vallejo
Unversidad de Medellin, Colombia
,
Pradeep K. Atrey
University at Albany, State University of New York, USA
,
M. Shamim Hossain
M. Shamim Hossain (King Saud University, KSA

Copyright © 2023 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 October 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Natural Science Foundation of China
Guangdong Basic and Applied Basic Research Foundation

Conference

MM '23

Sponsor:

SIGMM

MM '23: The 31st ACM International Conference on Multimedia

October 29 - November 3, 2023

Ottawa ON, Canada

Acceptance Rates

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
246
Total Downloads

Downloads (Last 12 months)148
Downloads (Last 6 weeks)14

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wu XLiu XNiu JWang HTang SZhu GSu HCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank DecompositionProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681588(7172-7181)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681588
Ling TShi SWang HHu CWang DCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Federated Morozov Regularization for Shortcut Learning in Privacy Preserving Learning with Watermarked Image DataProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681480(4899-4908)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681480
Jia RXie WLei JLi YCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Adaptive Hierarchical Aggregation for Federated Object DetectionProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681158(3732-3740)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681158
Zhao HZhang WSun HZhao YLiu YWang Z(2024)Personalized Fuzzy Federated Prompt Tuning for Re-Identification2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence (DTPI)10.1109/DTPI61353.2024.10778696(110-115)Online publication date: 18-Oct-2024
https://doi.org/10.1109/DTPI61353.2024.10778696

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten