Yu-Jie Xiong

CIDA: Class-wise Reliability Gating for Dual-Stream Few-Shot Adaptation of Vision-Language Models

Parameter-efficient adaptation of vision-language models such as CLIP typically modifies one side of the model, either the text prompt or the image features. When both sides are adapted, their predictions are merged with a weight fixed for the whole task, which cannot express that either branch may be more trustworthy...