The goal of domain generalization (DG) is to enhance the generalization capability of the
model learned from a source domain to other unseen domains. The recently developed …

Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …

To calculate the model accuracy on a computer vision task, eg, object recognition, we
usually require a test set composing of test samples and their ground truth labels. Whilst …

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (eg,
entropy minimization) to adapt the source pretrained model to the unlabeled target domain …

The success of automated medical image analysis depends on large-scale and expert-
annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a …

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained
vision-language models (VLMs) to various downstream tasks. In this work, we design a new …

Abstract Domain generalization (DG) is proposed to deal with the issue of domain shift,
which occurs when statistical differences exist between source and target domains …

The human visual system is remarkable in learning new visual concepts from just a few
examples. This is precisely the goal behind few-shot class incremental learning (FSCIL) …

Modeling interacting dynamical systems, such as fluid dynamics and intermolecular
interactions, is a fundamental research problem for understanding and simulating complex …

Abstract Out-of-distribution (OOD) generalization is a critical ability for deep learning models
in many real-world scenarios including healthcare and autonomous vehicles. Recently …