Preprint
Aug 2026
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...
Liang Wang, Haoyang Li, Chao Wang et al.
· 0 citations