ResCLIP: Residual Attention for Training-free Dense Vision-language Inference 事件

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference arXiv:2411.15851v2 Announce Type: replace Abstract: 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 modifyin