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 …

Abstract The field of Continual Learning investigates the ability to learn consecutive tasks
without losing performance on those previously learned. The efforts of researchers have …

Abstract Domain adaptation (DA) aims to transfer the knowledge learned from source
domain to an unlabeled target domain. Some recent works tackle source-free domain …

Conventional domain adaptation (DA) techniques aim to improve domain transferability by
learning domain-invariant representations; while concurrently preserving the task …

Unsupervised domain adaptation methods traditionally assume that all source categories
are present in the target domain. In practice, little may be known about the category overlap …

Unsupervised domain adaptation (DA) has gained substantial interest in semantic
segmentation. However, almost all prior arts assume concurrent access to both labeled …

Through prompting, large-scale pre-trained models have become more expressive and
powerful, gaining significant attention in recent years. Though these big models have zero …

Existing methods for unsupervised domain adaptation often rely on minimizing some
statistical distance between the source and target samples in the latent space. To avoid the …

In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …

This paper studies a new, practical but challenging problem, called Class-Incremental
Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all …