Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Deepfake detection remains a challenging task due to the difficulty of generalizing to new
types of forgeries. This problem primarily stems from the overfitting of existing detection …

Recently the proliferation of highly realistic synthetic images facilitated through a variety of
GANs and Diffusions has significantly heightened the susceptibility to misuse. While the …

The main challenge in domain generalization (DG) is to handle the distribution shift problem
that lies between the training and test data. Recent studies suggest that test-time training …

This paper offers a new perspective to ease the challenge of domain generalization, which
involves maintaining robust results even in unseen environments. Our design focuses on the …

Deepfake detection faces a critical generalization hurdle with performance deteriorating
when there is a mismatch between the distributions of training and testing data. A broadly …

Albeit the notable performance on in-domain test points, it is non-trivial for deep neural
networks to attain satisfactory accuracy when deploying in the open world, where novel …

Abstract Domain generalization (DG) enables generalizing a learning machine from multiple
seen source domains to an unseen target one. The general objective of DG methods is to …

Deepfake technology has given rise to a spectrum of novel and compelling applications.
Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive …

A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of
a standardized, unified, comprehensive benchmark. This issue leads to unfair performance …