Abstract
Increasingly stringent data privacy regulations limit the development of person re-identification (ReID) because person ReID training requires centralizing an enormous amount of data that contains sensitive personal information. To address this problem, we introduce federated person re-identification (FedReID)—implementing federated learning, an emerging distributed training method, to person ReID. FedReID preserves data privacy by aggregating model updates, instead of raw data, from clients to a central server. Furthermore, we optimize the performance of FedReID under statistical heterogeneity via benchmark analysis. We first construct a benchmark with an enhanced algorithm, two architectures, and nine person ReID datasets with large variances to simulate the real-world statistical heterogeneity. The benchmark results present insights and bottlenecks of FedReID under statistical heterogeneity, including challenges in convergence and poor performance on datasets with large volumes. Based on these insights, we propose three optimization approaches: (1) we adopt knowledge distillation to facilitate the convergence of FedReID by better transferring knowledge from clients to the server, (2) we introduce client clustering to improve the performance of large datasets by aggregating clients with similar data distributions, and (3) we propose cosine distance weight to elevate performance by dynamically updating the weights for aggregation depending on how well models are trained in clients. Extensive experiments demonstrate that these approaches achieve satisfying convergence with much better performance on all datasets. We believe that FedReID will shed light on implementing and optimizing federated learning on more computer vision applications.
- [1] . 2020. Federated learning based on dynamic regularization. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [2] . 2011. 3DPeS: 3D people dataset for surveillance and forensics. In Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding (J-HGBU’11). ACM, New York, NY, 59–64. Google Scholar
Digital Library
- [3] . 2018. LEAF: A benchmark for federated settings. CoRR abs/1812.01097 (2018). http://arxiv.org/abs/1812.01097.Google Scholar
- [4] . 2019. ABD-Net: Attentive but diverse person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 8351–8361.Google Scholar
Cross Ref
- [5] . 2020. FedHealth: A federated transfer learning framework for wearable healthcare. IEEE Intelligent Systems 35 (2020), 83–93.Google Scholar
Cross Ref
- [6] . 2011. Custom pictorial structures for re-identification. In Proceedings of the British Machine Vision Conference (BMVC’11).Google Scholar
Cross Ref
- [7] . 2017. EMNIST: Extending MNIST to handwritten letters. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN’17). IEEE, Los Alamitos, CA, 2921–2926.Google Scholar
Cross Ref
- [8] . 2019. EU Personal Data Protection in Policy and Practice. Springer.Google Scholar
Cross Ref
- [9] . 2012. Large scale distributed deep networks. In Advances in Neural Information Processing Systems 25, , , , and (Eds.). Curran Associates, 1223–1231. http://papers.nips.cc/paper/4687-large-scale-distributed-deep-networks.pdf.Google Scholar
- [10] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- [11] . 2008. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Proceedings of the European Conference on Computer Vision. 262–275.Google Scholar
Digital Library
- [12] . 2018. Edge AIBench: Towards comprehensive end-to-end edge computing benchmarking. In Proceedings of the 2018 BenchCouncil International Symposium on Benchmarking, Measuring, and Optimizing.Google Scholar
- [13] . 2016. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 770–778.Google Scholar
Cross Ref
- [14] . 2015. Distilling the knowledge in a neural network. In Proceedings of the NIPS Deep Learning and Representation Learning Workshop. http://arxiv.org/abs/1503.02531.Google Scholar
- [15] . 2011. Person re-identification by descriptive and discriminative classification. In Proceedings of the Scandinavian Conference on Image Analysis (SCIA’11). 91–102.Google Scholar
Cross Ref
- [16] . 2015. Deep transfer metric learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 325–333.Google Scholar
Cross Ref
- [17] . 2020. The OARF benchmark suite: Characterization and implications for federated learning systems. arXiv preprint arXiv:2006.07856 (2020).Google Scholar
- [18] . 2019. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 (2019).Google Scholar
- [19] . 2020. Scaffold: Stochastic controlled averaging for federated learning. In Proceedings of the International Conference on Machine Learning. 5132–5143.Google Scholar
- [20] . 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto, Toronto, Ontario.Google Scholar
- [21] . 2012. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (2012), 1097–1105.Google Scholar
Digital Library
- [22] . 2019. A survey of open-world person re-identification. IEEE Transactions on Circuits and Systems for Video Technology 30, 4 (2019), 1092–1108.Google Scholar
Cross Ref
- [23] . 2018. Learning to generalize: Meta-learning for domain generalization. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.Google Scholar
Cross Ref
- [24] . 2021. Model-contrastive federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10713–10722.Google Scholar
Cross Ref
- [25] . 2020. Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine 37 (2020), 50–60.Google Scholar
Cross Ref
- [26] . 2020. Federated optimization in heterogeneous networks. In Proceedings of the 3rd Machine Learning and Systems Conference (MLSys’20). 429–450.Google Scholar
- [27] . 2013. Locally aligned feature transforms across views. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. 3594–3601.Google Scholar
Digital Library
- [28] . 2012. Human reidentification with transferred metric learning. In Computer Vision—ACCV 2012. Lecture Notes in Computer Science, Vol. 7724. Springer, 31–44.Google Scholar
- [29] . 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 152–159.Google Scholar
Digital Library
- [30] . 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 152–159.Google Scholar
Digital Library
- [31] . 2016. Multi-scale triplet CNN for person re-identification. In Proceedings of the 24th ACM International Conference on Multimedia (MM’16). ACM, New York, NY, 192–196. Google Scholar
Digital Library
- [32] . 2014. Semi-supervised coupled dictionary learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3550–3557.Google Scholar
Digital Library
- [33] . 2013. Person re-identification by manifold ranking. In Proceedings of the 2013 IEEE International Conference on Image Processing. IEEE, Los Alamitos, CA, 3567–3571.Google Scholar
Cross Ref
- [34] . 2019. Real-world image datasets for federated learning.
arxiv:1910.11089 [cs.CV] (2019).Google Scholar - [35] . 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS’17). 1273–1282. http://proceedings.mlr.press/v54/mcmahan17a.html.Google Scholar
- [36] . 2020. FedFast: Going beyond average for faster training of federated recommender systems. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1234–1242.Google Scholar
Digital Library
- [37] . 2020. Billion-scale federated learning on mobile clients: A submodel design with tunable privacy. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. 1–14.Google Scholar
Digital Library
- [38] . 2016. Unsupervised cross-dataset transfer learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1306–1315.Google Scholar
Cross Ref
- [39] . 2019. Efficient parameter-free clustering using first neighbor relations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8934–8943.Google Scholar
Cross Ref
- [40] . 2018. Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745 (2018).Google Scholar
- [41] . 2018. Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation. In Proceedings of the International MICCAI Brain Lesion Workshop (BrainLes’18). 92–104.Google Scholar
- [42] . 2019. Generalizable person re-identification by domain-invariant mapping network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 719–728.Google Scholar
Cross Ref
- [43] . 2016. Deep attributes driven multi-camera person re-identification. In Proceedings of the European Conference on Computer Vision. 475–491.Google Scholar
Cross Ref
- [44] . 2022. GradientFlow: Optimizing network performance for large-scale distributed DNN training. IEEE Transactions on Big Data 8, 2 (2022), 495–507.Google Scholar
- [45] . 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV’18). 480–496.Google Scholar
Digital Library
- [46] . 2018. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM International Conference on Multimedia (MM’18). ACM, New York, NY, 274–282. Google Scholar
Digital Library
- [47] . 2020. Federated learning with matched averaging. In Proceedings of the International Conference on Learning Representations. https://openreview.net/forum?id=BkluqlSFDS.Google Scholar
- [48] . 2020. Tackling the objective inconsistency problem in heterogeneous federated optimization. arXiv preprint arXiv:2007.07481 (2020).Google Scholar
- [49] . 2014. Person re-identification by video ranking. In Computer Vision—ECCV 2014, , , , and (Eds.). Springer International Publishing, Cham, Switzerland, 688–703.Google Scholar
- [50] . 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 79–88.Google Scholar
Cross Ref
- [51] . 2021. Decentralised learning from independent multi-domain labels for person re-identification. Proceedings of the AAAI Conference on Artificial Intelligence 35, 4 (
May 2021), 2898–2906. https://ojs.aaai.org/index.php/AAAI/article/view/16396.Google ScholarCross Ref
- [52] . 2018. Local convolutional neural networks for person re-identification. In Proceedings of the 26th ACM International Conference on Multimedia (MM’18). ACM, New York, NY, 1074–1082. Google Scholar
Digital Library
- [53] . 2019. Federated learning with unbiased gradient aggregation and controllable meta updating. In Proceedings of the NIPS Federated Learning for Data Privacy and Confidentiality Workshop.Google Scholar
- [54] . 2021. Deep learning for person re-identification: A survey and outlook. arXiv:2001.04193 (2021).Google Scholar
- [55] . 2021. Federated learning for non-IID data via unified feature learning and optimization objective alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4420–4428.Google Scholar
Cross Ref
- [56] . 2018. Federated learning with non-IID data. CoRR abs/1806.00582 (2018). http://arxiv.org/abs/1806.00582.Google Scholar
- [57] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV’15).1116–1124.Google Scholar
Cross Ref
- [58] . 2016. Person re-identification: Past, present and future. CoRR abs/1610.02984 (2016). http://arxiv.org/abs/1610.02984.Google Scholar
- [59] . 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE International Conference on Computer Vision.Google Scholar
Cross Ref
- [60] . 2022. EasyFL: A low-code federated learning platform for dummies. IEEE Internet of Things Journal. Early access, January 20, 2022. Google Scholar
Cross Ref
- [61] . 2021. Collaborative unsupervised visual representation learning from decentralized data. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4912–4921.Google Scholar
Cross Ref
- [62] . 2022. Divergence-aware federated self-supervised learning. In Proceedings of the International Conference on Learning Representations. https://openreview.net/forum?id=oVE1z8NlNe.Google Scholar
- [63] . 2020. Performance optimization of federated person re-identification via benchmark analysis. In Proceedings of the 28th ACM International Conference on Multimedia. 955–963.Google Scholar
Digital Library
Index Terms
Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
Recommendations
Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
MM '21: Proceedings of the 29th ACM International Conference on MultimediaPerson 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 ...
Performance Optimization of Federated Person Re-identification via Benchmark Analysis
MM '20: Proceedings of the 28th ACM International Conference on MultimediaFederated 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 ...
Optimizing Train-Test Data for Person Re-Identification in Real-World Applications
ICMVA '22: Proceedings of the 2022 5th International Conference on Machine Vision and ApplicationsPerson re-identification (re-ID) aims to recognize an identity in non-overlapping camera views. Recently, re-ID received increased attention due to the growth of deep learning and its prominent applications in the field of automated video surveillance. ...






Comments