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 …

Recent years have witnessed great progress in deep learning based object detection.
However, due to the domain shift problem, applying off-the-shelf detectors to an unseen …

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 …

Recent years have witnessed great progress in object detection. However, due to the
domain shift problem, applying the knowledge of an object detector learned from one …

Unsupervised domain adaptation has attracted growing research attention on semantic
segmentation. However, 1) most existing models cannot be directly applied into lesions …

Large language models (LLMs), while exhibiting exceptional performance, suffer from
hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment …

Learning methods are challenged when there is not enough labelled data. It gets worse
when the existing learning data have different distributions in different domains. To deal with …

Existing domain adaptation approaches often try to reduce distribution difference between
source and target domains and respect domain-specific discriminative structures by some …

On the one hand, deep neural networks are effective in learning large datasets. On the
other, they are inefficient with their data usage. They often require copious amount of …

To bridge source and target domains for domain adaptation, there are three important types
of information including data structure, domain label, and class label. Most existing domain …