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 (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 …

Convolutional neural network-based approaches have achieved remarkable progress in
semantic segmentation. However, these approaches heavily rely on annotated data which …

Unsupervised domain adaptation (UDA) aims to improve the classification performance on
an unlabeled target domain by leveraging information from a fully labeled source domain …

Unsupervised domain adaptation has recently emerged as an effective paradigm for
generalizing deep neural networks to new target domains. However, there is still enormous …

Different distribution shifts require different algorithmic and operational interventions.
Methodological research must be grounded by the specific shifts they address. Although …

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively
generates pseudo labels on unlabeled target data and retrains the network. However …

Generalizing deep neural networks to new target domains is critical to their real-world utility.
In practice, it may be feasible to get some target data labeled, but to be cost-effective it is …

Abstract Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-
domain tasks recently. Though preliminary progress has been made, the performance gap …

Active domain adaptation (ADA) aims to improve the model adaptation performance by
incorporating the active learning (AL) techniques to label a maximally-informative subset of …