In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Abstract Single Domain Generalization (SDG) tackles the problem of training a model on a
single source domain so that it generalizes to any unseen target domain. While this has …

Object detectors often suffer from the domain gap between training (source domain) and real-
world applications (target domain). Mean-teacher self-training is a powerful paradigm in …

Recent advances in deep learning have led to the development of accurate and efficient
models for various computer vision applications such as classification, segmentation, and …

Self-training approaches recently achieved promising results in cross-domain object
detection, where people iteratively generate pseudo labels for unlabeled target domain …

Object detection at night is a challenging problem due to the absence of night image
annotations. Despite several domain adaptation methods, achieving high-precision results …

The task of weakly supervised temporal sentence grounding aims at finding the
corresponding temporal moments of a language description in the video, given video …

This work focuses on a practical knowledge transfer task defined as Source-Free
Unsupervised Domain Adaptation (SFUDA), where only a well-trained source model and …

Abstract Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source
domain to tackle the learning tasks on the unlabeled target domain. It can be more …

Abstract Domain adaptive Object Detection (DAOD) leverages a labeled domain (source) to
learn an object detector generalizing to a novel domain without annotation (target). Recent …