AI RESEARCH
ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
arXiv CS.CV
•
ArXi:2411.15851v2 Announce Type: replace While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such deficiency in dense predictions to the self-attention layers in the final block, and have achieved commendable results by modifying the original query-key attention to self-correlation attention, (e.g., query-query and key-key attention.