Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting
and enhance their generalization and performance, various methods have been suggested …

Adversarial learning has achieved remarkable performances for unsupervised domain
adaptation (UDA). Existing adversarial UDA methods typically adopt an additional …

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

Abstract Domain Adaptation aims to transfer the knowledge learned from a labeled source
domain to an unlabeled target domain whose data distributions are different. However, the …

Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in
the unlabeled target domain using the pre-trained source model, not the source data …

Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the
labeled source domain's knowledge to improve the model's discriminability on the unlabeled …

Unsupervised domain adaptation (UDA) approaches focus on adapting models trained on a
labeled source domain to an unlabeled target domain. In contrast to UDA, source-free …

Transfer learning (TL) utilizes data or knowledge from one or more source domains to
facilitate learning in a target domain. It is particularly useful when the target domain has very …

The performance of nighttime semantic segmentation is restricted by the poor illumination
and a lack of pixel-wise annotation, which severely limit its application in autonomous …