Haoyang Li

PPOM: Marginalizing Patch-Grid Phase for CLIP-Based Generalizable Vision-Language Prompt Tuning

Prompt tuning adapts CLIP-based vision-language models with few trainable parameters, yet its predictions remain sensitive to the spatial sampling imposed by a frozen vision transformer. In particular, non-overlapping patch tokenization makes predictions depend on the alignment (phase) between image and the patch latti...