2025
When Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective
ICASSP 2025accepted
Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution tasks. On the other hand, linear probing, a standard transfe…