相关论文: FedSDAF: Leveraging Source Domain Awareness for En…

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…

Though feature-alignment based Domain Adaptive Object Detection (DAOD) methods have achieved remarkable progress, they ignore the source bias issue, i.e., the detector tends to acquire more source-specific knowledge, impeding its…

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of…

Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains with both domain shifts and label shifts. The scarcity of the source domain and the…

Federated Graph Learning (FGL) has demonstrated the advantage of training a global Graph Neural Network (GNN) model across distributed clients using their local graph data. Unlike Euclidean data (\eg, images), graph data is composed of…

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while…

Federated adversary domain adaptation is a unique distributed minimax training task due to the prevalence of label imbalance among clients, with each client only seeing a subset of the classes of labels required to train a global model. To…

In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…

Existing federated learning models that follow the standard risk minimization paradigm of machine learning often fail to generalize in the presence of spurious correlations in the training data. In many real-world distributed settings,…

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the…

Existing domain generalization methods for face anti-spoofing endeavor to extract common differentiation features to improve the generalization. However, due to large distribution discrepancies among fake faces of different domains, it is…

Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…

Due to the scarcity of industrial data, individual equipment users, particularly start-ups, struggle to independently train a comprehensive fault diagnosis model; federated learning enables collaborative training while ensuring data…

Federated Graph Learning (FGL) is an emerging technology that enables clients to collaboratively train powerful Graph Neural Networks (GNNs) in a distributed manner without exposing their private data. Nevertheless, FGL still faces the…

In privacy-preserving mobile network transmission scenarios with heterogeneous client data, personalized federated learning methods that decouple feature extractors and classifiers have demonstrated notable advantages in enhancing learning…

With the wealth of information produced by social networks, smartphones, medical or financial applications, speculations have been raised about the sensitivity of such data in terms of users' personal privacy and data security. To address…

Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In…

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real-world and possibly causes data-privacy issues, especially when…