Images taken between 2013 and 2015 are used as the validation set.

To compare thequality oftargetsamples being selected fortraining, wemeasure reliability precision (howmanyofthe selected target samples were actually predicted correctly?) We report expected calibration error (ECE [7]), lower is better. We separately visualize features before and after in-domain pretraining with MAE 7and DINO 8. Wenote that these features are completely selfsupervised as the model has not seen task labels yet. Regardless, we observe a small degree of taskdiscriminativeness (examples ofthesame class areclustered together) anddomain invariance (examples of the same class but different domains are close) before additional pretraining. We now measure the degree of label overlap between ImageNet-22K and these 3 benchmarks.

--Despite the remarkable performance of vision language models (VLMs) such as Contrastive Language Image Pre-training (CLIP), the large size of these models is a considerable obstacle to their use in federated learning (FL) systems where the parameters of local client models need to be transferred to a global server for aggregation. Another challenge in FL is the heterogeneity of data from different clients, which affects the generalization performance of the solution. In addition, natural pre-trained VLMs exhibit poor generalization ability in the medical datasets, suggests there exists a domain gap. T o solve these issues, we introduce a novel method for the Federated Adversarial Adaptation (F AA) of CLIP . Our method, named F AA-CLIP, handles the large communication costs of CLIP using a light-weight feature adaptation module (F AM) for aggregation, effectively adapting this VLM to each client's data while greatly reducing the number of parameters to transfer . By keeping CLIP frozen and only updating the F AM parameters, our method is also computationally efficient. Unlike existing approaches, our F AA-CLIP method directly addresses the problem of domain shifts across clients via a domain adaptation (DA) module. This module employs a domain classifier to predict if a given sample is from the local client or the global server, allowing the model to learn domain-invariant representations. Extensive experiments on six different datasets containing both natural and medical images demonstrate that F AA-CLIP can generalize well on both natural and medical datasets compared to recent FL approaches. Our codes are available at https://github.com/AIPMLab/F While models based on deep learning (DL) have achieved ground-breaking results in a broad range of computer vision and natural language understanding tasks, their performance is often dependent on the availability of large datasets [1]. In recent years, there has been a growing concern on ensuring data privacy and security, with many organizations implementing regulations and laws such as the EU General Data Protection Regulation (GDPR) [2]. These restrictions on sharing raw data from different organizations poses a siginificant challenge for training robust DL models in fields like medical imaging where privacy is of utmost importance. One of the most promising solutions to this problem is federated learning (FL).

In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label smoothing at the client level to prevent overfitting to domain-specific features, thereby enhancing generalization capabilities across diverse domains when aggregating local models into a global model. Additionally, FedSB incorporates a decentralized budgeting mechanism which balances training among clients, which is shown to improve the performance of the aggregated global model. Extensive experiments on four commonly used multi-domain datasets, PACS, VLCS, OfficeHome, and TerraInc, demonstrate that FedSB outperforms competing methods, achieving state-of-the-art results on three out of four datasets, indicating the effectiveness of FedSB in addressing data heterogeneity.