Performance Optimization of Federated Person Re-identification via Benchmark Analysis
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Federated learning is a privacy-preserving machine learning technique that learns a shared model across decentralized clients. It can alleviate privacy concerns of personal re-identification, an important computer vision task. In this work, we implement federated learning to person re-identification (FedReID) and optimize its performance affected by statistical heterogeneity in the real-world scenario. We first construct a new benchmark to investigate the performance of FedReID. This benchmark consists of (1) nine datasets with different volumes sourced from different domains to simulate the heterogeneous situation in reality, (2) two federated scenarios, and (3) an enhanced federated algorithm for FedReID. The benchmark analysis shows that the client-edge-cloud architecture, represented by the federated-by-dataset scenario, has better performance than client-server architecture in FedReID. It also reveals the bottlenecks of FedReID under the real-world scenario, including poor performance of large datasets caused by unbalanced weights in model aggregation and challenges in convergence. Then we propose two optimization methods: (1) To address the unbalanced weight problem, we propose a new method to dynamically change the weights according to the scale of model changes in clients in each training round; (2) To facilitate convergence, we adopt knowledge distillation to refine the server model with knowledge generated from client models on a public dataset. Experiment results demonstrate that our strategies can achieve much better convergence with superior performance on all datasets. We believe that our work will inspire the community to further explore the implementation of federated learning on more computer vision tasks in real-world scenarios.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · cited 1×
“Statistical heterogeneity— data with non-identical and independent distribution (non-IID) and unbalanced volumes—is one of the key challenges for FedReID in the real-world scenario [12].”
BackgroundFederated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
Wei, L., Zhang, S., Gao, W., & Tian, Q. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00016 · Cited by 2,118
Self-citationFederated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077
Cited by
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., & He, B. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3124599 · Cited by 1,407
“[227] utilize benchmark analysis to improve the performance of federated person reidentification.”
BackgroundMethodModel aggregation techniques in federated learning: A comprehensive survey
Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G., & Piccialli, F. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2023.09.008 · Cited by 452
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
Zhang, L., Shen, L., Ding, L., Tao, D., & Duan, L.-Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00993 · Cited by 371
Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles
Zhang, Z., Wang, S., Hong, Y., Zhou, L., & Hao, Q. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561612 · Cited by 76
“On the other hand, deep network models trained at the cloud [4]–[9], [11], [14], [15] assume that training datasets have been properly labeled, but real-world applications require label generation for new data samples during online learning procedures via knowledge transfer from “teacher” models to “student” models [1…”
BackgroundBai, F., Wu, J., Shen, P., Li, S., & Zhou, S. (2021) · arXiv · doi:10.48550/arxiv.2105.02501 · Cited by 21
Metadata
- Authors
- Zhuang, W., Wen, Y., Zhang, X., Gan, X., Yin, D., Zhou, D., Zhang, S., & Yi, S.
- Venue
- Proceedings of the 28th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2020-10-12
- Pages
- 955-963
- OpenAlex
- W3080411117
- Cited by
- 94
- References
- 4
- FWCI
- 4.74
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.