Abstract Domain adaptation (DA) aims to alleviate the domain shift between source domain
and target domain. Most DA methods require access to the source data, but often that is not …

Domain adaptation (DA) aims to alleviate the domain shift between source domain and
target domain. Most DA methods require access to the source data, but often that is not …

In this paper, we propose a novel domain adaptation method for the source-free setting. In
this setting, we cannot access source data during adaptation, while unlabeled target data …

We propose a simple but effective source-free domain adaptation (SFDA) method. Treating
SFDA as an unsupervised clustering problem and following the intuition that local neighbors …

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 …

Over the past decade, domain adaptation has become a widely studied branch of transfer
learning which aims to improve performance on target domains by leveraging knowledge …

Deep neural networks, trained with large amount of labeled data, can fail to generalize well
when tested with examples from a target domain whose distribution differs from the training …

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 …

Domain adaptation aims to leverage a label-rich domain (the source domain) to help model
learning in a label-scarce domain (the target domain). Most domain adaptation methods …

Domain adaptation assumes that samples from source and target domains are freely
accessible during a training phase. However, such an assumption is rarely plausible in the …