Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …

The learning of the deep networks largely relies on the data with human-annotated labels. In
some label insufficient situations, the performance degrades on the decision boundary with …

Earlier work demonstrates the promise of deep-learning-based approaches for point cloud
segmentation; however, these approaches need to be improved to be practically useful. To …

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 …

Abstract Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-
labeled source domain to an unlabeled target domain. In some applications, however, it is …

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging
knowledge from a source domain. Existing methods either attempt to align the cross-domain …

In unsupervised domain adaptation, rich domain-specific characteristics bring great
challenge to learn domain-invariant representations. However, domain discrepancy is …

To improve the generalization of detectors, for domain adaptive object detection (DAOD),
recent advances mainly explore aligning feature-level distributions between the source and …

Pedestrian trajectory prediction is an essential component in a wide range of AI applications
such as autonomous driving and robotics. Existing methods usually assume the training and …

Abstract Domain adaptation (DA) paves the way for label annotation and dataset bias issues
by the knowledge transfer from a label-rich source domain to a related but unlabeled target …