Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models

• URL: http://arxiv.org/abs/2509.08372v1
• Date: Wed, 10 Sep 2025 08:10:57 GMT
• Title: Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
• Authors: Kosuke Kihara, Junki Mori, Taiki Miyagawa, Akinori F. Ebihara,
• Abstract summary: Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client.<n>We propose replacing the FFREEDA backbone with a frozen vision foundation model (VFM)<n>VFMs effectively mitigate the effects of domain gaps, class imbalances, and even non-IID-ness among target clients.
• Score: 9.432150710329609
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client. Recently, research has focused on Federated Source-Free Domain Adaptation (FFREEDA), a more realistic scenario wherein client-held target domain data remains unlabeled, and the server can access source domain data only during pre-training. We extend this framework to a more complex and realistic setting: Class Imbalanced FFREEDA (CI-FFREEDA), which takes into account class imbalances in both the source and target domains, as well as label shifts between source and target and among target clients. The replication of existing methods in our experimental setup lead us to rethink the focus from enhancing aggregation and domain adaptation methods to improving the feature extractors within the network itself. We propose replacing the FFREEDA backbone with a frozen vision foundation model (VFM), thereby improving overall accuracy without extensive parameter tuning and reducing computational and communication costs in federated learning. Our experimental results demonstrate that VFMs effectively mitigate the effects of domain gaps, class imbalances, and even non-IID-ness among target clients, suggesting that strong feature extractors, not complex adaptation or FL methods, are key to success in the real-world FL.

Related papers

• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation [9.231185930198162]
  Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain without access to source data.<n>Recent advances in Foundation Models (FMs) have introduced new opportunities for leveraging external semantic knowledge to guide SFDA.
  arXiv  Detail & Related papers  (2025-11-24T14:12:22Z)
• SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning [15.256986486372407]
  Spiking federated learning allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. Existing spiking federated learning methods employ a random selection approach for client aggregation, assuming unbiased client participation. We propose a credit assignment-based active client selection strategy, the SFedCA, to judiciously aggregate clients that contribute to the global sample distribution balance.
  arXiv  Detail & Related papers  (2024-06-18T01:56:22Z)
• Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training [23.56208527227504]
  Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. In the conventional SFDA pipeline, a large data (e.g. ImageNet) pre-trained feature extractor is used to initialize the source model. We introduce an integrated framework to incorporate pre-trained networks into the target adaptation process.
  arXiv  Detail & Related papers  (2024-05-05T14:48:13Z)
• Efficient Cross-Domain Federated Learning by MixStyle Approximation [0.3277163122167433]
  We introduce a privacy-preserving, resource-efficient Federated Learning concept for client adaptation in hardware-constrained environments. Our approach includes server model pre-training on source data and subsequent fine-tuning on target data via low-end clients. Preliminary results indicate that our method reduces computational and transmission costs while maintaining competitive performance on downstream tasks.
  arXiv  Detail & Related papers  (2023-12-12T08:33:34Z)
• Federated Active Learning for Target Domain Generalisation [20.582521330618768]
  We introduce FEDALV, composed of Active Learning (AL) and Federated Domain Generalisation (FDG) FDG enables generalisation of an image classification model trained from limited source domain client's data without sharing images to an unseen target domain. FedaLV manages to obtain the performance of the full training target accuracy while sampling as little as 5% of the source client's data.
  arXiv  Detail & Related papers  (2023-12-04T14:50:23Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• FACT: Federated Adversarial Cross Training [0.0]
  Federated Adrial Cross Training (FACT) uses implicit domain differences between source clients to identify domain shifts in the target domain. We empirically show that FACT outperforms state-of-the-art federated, non-federated and source-free domain adaptation models.
  arXiv  Detail & Related papers  (2023-06-01T12:25:43Z)
• Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework [82.36466358313025]
  We propose a primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model. Experiments based on (semi-supervised) image classification tasks demonstrate superiority of FedVRA over the existing schemes.
  arXiv  Detail & Related papers  (2022-12-03T03:27:51Z)
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation [80.03883315743715]
  Source-free domain adaptation transits the source-trained model towards target domain without exposing the source data. This paradigm is still at risk of data leakage due to adversarial attacks on the source model. We propose a novel approach named RAIN (RegulArization on Input and Network) for Black-Box domain adaptation from both input-level and network-level regularization.
  arXiv  Detail & Related papers  (2022-08-22T18:18:47Z)
• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning [87.08902493524556]
  Federated learning(FL) has recently attracted increasing attention from academia and industry. We propose FedDM to build the global training objective from multiple local surrogate functions. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data.
  arXiv  Detail & Related papers  (2022-07-20T04:55:18Z)
• FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction [48.85303253333453]
  Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. We propose a novel federated learning algorithm with local drift decoupling and correction (FedDC) Our FedDC only introduces lightweight modifications in the local training phase, in which each client utilizes an auxiliary local drift variable to track the gap between the local model parameter and the global model parameters. Experiment results and analysis demonstrate that FedDC yields expediting convergence and better performance on various image classification tasks.
  arXiv  Detail & Related papers  (2022-03-22T14:06:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.