The vision-language model has brought great improvement to few-shot industrial anomaly
detection which usually needs to design of hundreds of prompts through prompt …

Vision-centric autonomous driving has recently raised wide attention due to its lower cost.
Pre-training is essential for extracting a universal representation. However current vision …

Referring image segmentation (RIS) aims to segment the target referent described by
natural language. Recently large-scale pre-trained models eg CLIP and SAM have been …

Learning from a limited amount of data namely Few-Shot Learning stands out as a
challenging computer vision task. Several works exploit semantics and design complicated …

Current multi-instance learning algorithms for pathology image analysis often require a
substantial number of Whole Slide Images for effective training but exhibit suboptimal …

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation
(FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially …

Few-shot classification learns from a small number of image samples to recognize unseen
images. Recent few-shot learning exploits auxiliary text information, such as class labels …

Restricted by the deficient training samples, deep learning-based automatic target
recognition (ATR) methods for synthetic aperture radar (SAR) are prone to performance …

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual
samples. Existing approaches attempt to incorporate semantic information into the limited …

Abstract While recent Vision-Language (VL) models excel at open-vocabulary tasks it is
unclear how to use them with specific or uncommon concepts. Personalized Text-to-Image …