X
Xin Gan
Researcher at SenseTime
Publications - 7
Citations - 104
Xin Gan is an academic researcher from SenseTime. The author has contributed to research in topics: Computer science & Information privacy. The author has an hindex of 3, co-authored 5 publications receiving 27 citations.
Papers
More filters
Proceedings ArticleDOI
Performance Optimization for Federated Person Re-identification via Benchmark Analysis
Weiming Zhuang,Yonggang Wen,Xuesen Zhang,Xin Gan,Daiying Yin,Dongzhan Zhou,Shuai Zhang,Shuai Yi +7 more
TL;DR: This work implements federated learning to person re-identification (FedReID) and optimize its performance affected by statistical heterogeneity in the real-world scenario, and proposes two optimization methods to address the unbalanced weight problem and facilitate convergence.
Proceedings ArticleDOI
Performance Optimization of Federated Person Re-identification via Benchmark Analysis
Weiming Zhuang,Yonggang Wen,Xuesen Zhang,Xin Gan,Daiying Yin,Dongzhan Zhou,Shuai Zhang,Shuai Yi +7 more
TL;DR: Wang et al. as discussed by the authors implemented federated learning to person re-ID (FedReID) and optimize its performance affected by statistical heterogeneity in the real-world scenario.
Posted Content
Collaborative Unsupervised Visual Representation Learning from Decentralized Data.
TL;DR: In this article, a federated unsupervised learning framework, FedU, is proposed, where each party trains models from unlabeled data independently using contrastive learning with an online network and a target network.
Proceedings ArticleDOI
Federated Unsupervised Domain Adaptation for Face Recognition
TL;DR: This work proposes federated unsupervised do-main adaptation for face recognition, FedFR, which jointly optimizes clustering-based domain adaptation and federated learning to elevate performance on the target domain.
Posted Content
Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning.
TL;DR: Zhang et al. as mentioned in this paper proposed a novel unsupervised federated face recognition approach (FedFR), which improves the performance in the target domain by iteratively aggregating knowledge from the source domain through federated learning.