Following unprecedented success on the natural language tasks, Transformers have been
successfully applied to several computer vision problems, achieving state-of-the-art results …

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 …

Vision-language models (VLMs) such as CLIP have shown promising performance on a
variety of recognition tasks using the standard zero-shot classification procedure--computing …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

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 …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

This paper presents a new algorithm for domain generalization (DG),\textit {test-time
template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift. Unlike …

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging
visual learning tasks, which can be cast as a feature distribution matching problem. With the …