Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or (DG) techniques address this problem. However, the target is often unknown during training which limits utilization of DA methods. DG can conquer by learning invariant features without seein...

Unsupervised Domain Adaptation (UDA) aims at learning a classifier for an unlabeled target domain by transferring knowledge from labeled source with related but different distribution. The strategy of aligning the two domains in latent feature space via metric discrepancy or adversarial has achieved considerable progress. However, these existing approaches mainly focus on adapting entire image ...

Breakthroughs in unsupervised domain adaptation (uDA) can help adapting models from a label-rich source to unlabeled target domains. Despite these advancements, there is lack of research on how uDA algorithms, particularly those based adversarial learning, work distributed settings. In real-world applications, domains are often across thousands devices, and existing algorithms -- which centrali...

Training an object detection model often requires numerous annotated images on a centralized host, which may violate user privacy and data confidentiality. Federated learning (FL) resolves this issue by allowing multiple clients, e.g., cameras, to collaboratively train while protecting privacy. However, models trained with FL fail be generalized for new target domain due shift when the between ...

The emerging paradigm of Federated Learning enables mobile users to collaboratively train a model without disclosing their privacy-sensitive data. Nevertheless, data collected from different may not be independent and identically distributed. Thus directly applying the trained new user usually leads performance degradation due so-called domain shift. Unsupervised Domain Adaptation is an effecti...