Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Research in the medical imaging field using deep learning approaches has become
progressively contingent. Scientific findings reveal that supervised deep learning methods' …

Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with
only unlabeled test data streams. Most of the previous TTA methods have achieved great …

Abstract Domain generalization (DG) aims to generalize a model trained on multiple source
(ie, training) domains to a distributionally different target (ie, test) domain. In contrast to the …

Though remarkable progress has been achieved in various vision tasks, deep neural
networks still suffer obvious performance degradation when tested in out-of-distribution …

Deep learning models usually suffer from the domain shift issue, where models trained on
one source domain do not generalize well to other unseen domains. In this work, we …

Adversarial data augmentation has shown promise for training robust deep neural networks
against unforeseen data shifts or corruptions. However, it is difficult to define heuristics to …

While agents trained by Reinforcement Learning (RL) can solve increasingly challenging
tasks directly from visual observations, generalizing learned skills to novel environments …

Most successful self-supervised learning methods are trained to align the representations of
two independent views from the data. State-of-the-art methods in video are inspired by …