Federated Unsupervised Visual Representation Learning via Exploiting General Content and Personal Style
Discriminative unsupervised learning methods such as contrastive learning have demonstrated the ability to learn generalized visual representations on centralized data. It is nonetheless challenging to adapt such methods to a distributed system with unlabeled, private, and heterogeneous client data due to user styles and preferences. Federated learning enables multiple clients to collectively learn a global model without provoking any privacy breach between local clients. On the other hand, another direction of federated learning studies personalized methods to address the local heterogeneity. However, work on solving both generalization and personalization without labels in a decentralized setting remains unfamiliar. In this work, we propose a novel method, FedStyle, to learn a more generalized global model by infusing local style information with local content information for contrastive learning, and to learn more personalized local models by inducing local style information for downstream tasks. The style information is extracted by contrasting original local data with strongly augmented local data (Sobel filtered images). Through extensive experiments with linear evaluations in both IID and non-IID settings, we demonstrate that FedStyle outperforms both the generalization baseline methods and personalization baseline methods in a stylized decentralized setting. Through comprehensive ablations, we demonstrate our design of style infusion and stylized personalization improve performance significantly.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningFederated LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FORLA:Federated Object-centric Representation Learning with Slot Attention
Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative acros…
DecoderFederated LearningObject DiscoveryRepresentation LearningFedX: Unsupervised Federated Learning with Cross Knowledge Distillation
This paper presents FedX, an unsupervised federated learning framework. Our model learns unbiased representation from decentralized and heterogeneous local data. It employs a two-sided knowledge distillation with contras…
Contrastive LearningFederated LearningKnowledge DistillationFederated Unsupervised Semantic Segmentation
This work explores the application of Federated Learning (FL) in Unsupervised Semantic image Segmentation (USS). Recent USS methods extract pixel-level features using frozen visual foundation models and refine them throu…
Federated LearningImage SegmentationSegmentationSemantic Segmentation+1Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation
Exploiting deep learning in medical imaging faces critical challenges, including strict privacy constraints, heterogeneous imaging devices with varying acquisition properties, and class imbalance due to the uneven preval…
Medical Image ClassificationFederated LearningTowards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
While supervised federated learning approaches have enjoyed significant success, the domain of unsupervised federated learning remains relatively underexplored. Several federated EM algorithms have gained popularity in p…
Federated Learning