Recently, pre-trained vision-language models have been increasingly used to tackle the
challenging zero-shot segmentation task. Typical solutions follow the paradigm of first …

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to
new or under-trained data distributions without re-training. Nevertheless, during the …

Abstract Out-of-distribution (OOD) generalization, where the model needs to handle
distribution shifts from training, is a major challenge of machine learning. Contrastive …

We show that raw degradation features can effectively guide deep restoration models,
providing accurate degradation priors to facilitate better restoration. While networks that do …

The visual classification performance of vision-language models such as CLIP has been
shown to benefit from additional semantic knowledge from large language models (LLMs) …

Sketches are highly expressive, inherently capturing subjective and fine-grained visual
cues. The exploration of such innate properties of human sketches has, however, been …

Large vision-language models (VLMs) have achieved substantial progress in multimodal
perception and reasoning. Furthermore, when seamlessly integrated into an embodied …

Face anti-spoofing (FAS) or presentation attack detection is an essential component of face
recognition systems deployed in security-critical applications. Existing FAS methods have …

Test-time adaptation (TTA) is a special and practical setting in unsupervised domain
adaptation, which allows a pre-trained model in a source domain to adapt to unlabeled test …

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view
discrepancy issue in 3D visual grounding. However, existing methods normally neglect the …