2 papers
cs.CV2026
PCLM: Small-target localization with frozen CLIP via prototype contrast and local magnification
Zhipeng Ye, Feng Jiang, Qiufeng Wang +1
Small targets occupy few patches in a vision-language encoder, so spatial features often mix object appearance with surrounding content. We propose Prototype Contrast and Local Mag…
cs.CV2025
IDEA: Image Description Enhanced CLIP-Adapter
Zhipeng Ye, Feng Jiang, Qiufeng Wang +2
CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot…