Natural polysaccharides, which are described in this study, are some of the most extensively
used biopolymers in food, pharmaceutical, and medical applications, because they are …

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-
KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M …

Deep learning grew in importance in recent years due to its versatility and excellent
performance on supervised classification tasks. A core assumption for such supervised …

Domain adaptation investigates the problem of cross-domain knowledge transfer where the
labeled source domain and unlabeled target domain have distinctive data distributions …

Black-box domain adaptation treats the source domain model as a black box. During the
transfer process, the only available information about the target domain is the noisy labels …

In this paper, we study the task of source-free domain adaptation (SFDA), where the source
data are not available during target adaptation. Previous works on SFDA mainly focus on …

Unsupervised domain adaptation, which aims to alleviate the domain shift between source
domain and target domain, has attracted extensive research interest; however, this is …

The discriminability and transferability of models are two important factors for the success of
domain adaptation methods. Recently, some domain adaptation methods have improved …

Domain adaptation for classification has achieved significant progress in natural images but
not in remote-sensing images due to huge differences in data-imaging mechanisms …

Although adversarial domain adaptation enhances feature transferability, the feature
discriminability will be degraded in the process of adversarial learning. Moreover, most …