Software defect prediction (SDP) is very helpful for optimizing the resource allocation of
software testing and improving the quality of software products. The cross-project defect …

In unsupervised domain adaptation (UDA), a target-domain model is trained by the
supervised knowledge from a source domain. Although UDA has recently received much …

The research of semantic segmentation based on unsupervised domain adaptation greatly
alleviates the high-cost bottleneck of manual annotation in deep learning. Inevitably domain …

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to
unlabeled target domain. The semi-supervised method based on mean-teacher framework …

Weakly-supervised learning has attracted growing research attention on medical lesions
segmentation due to significant saving in pixel-level annotation cost. However, 1) most …

Since human-labeled samples are free for the target set, unsupervised person re-
identification (Re-ID) has attracted much attention in recent years, by additionally exploiting …

Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in
real-world scenarios, which relaxes the assumption in conventional Unsupervised Domain …

Unsupervised domain adaptation aims to leverage knowledge from a labeled source
domain to learn an accurate model in an unlabeled target domain. However, many previous …

Domain adaptation aims to transfer the knowledge learned from a labeled source domain to
an unlabeled target domain, which has different data distribution with the source domain …

In domain adaptation (DA), label-induced losses generally occupy a dominant position and
most previous models regard hard or soft labels as their inputs. However, these two types of …