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 …

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 …

Many recent machine learning tasks focus to develop models that can generalize to unseen
distributions. Domain generalization (DG) has become one of the key topics in various fields …

Image-language models with prompt learning have shown remarkable advances in
numerous downstream vision tasks. Nevertheless conventional prompt learning methods …

Deep networks trained on the source domain show degraded performance when tested on
unseen target domain data. To enhance the model's generalization ability, most existing …

Canonical work handling distribution shifts typically necessitates an entire target distribution
that lands inside the training distribution. However, practical scenarios often involve only a …

In domain generalization (DG), the target domain is unknown when the model is being
trained, and the trained model should successfully work on an arbitrary (and possibly …

Deep learning models fail on cross-domain challenges if the model is oversensitive to
domain-specific attributes, eg, lightning, background, camera angle, etc. To alleviate this …

The generalization capability of machine learning systems degenerates notably when the
test distribution drifts from the training distribution. Recently, Domain Generalization (DG) …

In this paper, we propose energy-based sample adaptation at test time for domain
generalization. Where previous works adapt their models to target domains, we adapt the …