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 …

The world we see is ever-changing and it always changes with people, things, and the
environment. Domain is referred to as the state of the world at a certain moment. A research …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging
visual learning tasks, which can be cast as a feature distribution matching problem. With the …

The research progress in multimodal learning has grown rapidly over the last decade in
several areas, especially in computer vision. The growing potential of multimodal data …

Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

We present a physics-based humanoid controller that achieves high-fidelity motion imitation
and fault-tolerant behavior in the presence of noisy input (eg pose estimates from video or …

Recent advances in domain adaptation show that deep self-training presents a powerful
means for unsupervised domain adaptation. These methods often involve an iterative …

The divergence between labeled training data and unlabeled testing data is a significant
challenge for recent deep learning models. Unsupervised domain adaptation (UDA) …

Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant
representations to narrow the domain shift, which are empirically effective but theoretically …