
This research paper introduces a novel prompt tuning method for Vision-Language Models (VLMs) that enhances their ability to generalize to unseen classes while maintaining strong performance on seen classes.


coremsg

improving-the-generalizability-of-prompt-tuning-for-vision-language-models


Improving the Generalizability of Prompt Tuning for Vision-Language Models


title_rewrite


Increasing the information density of prompts can significantly improve the generalization ability of vision-language models, while drastically reducing the number of tunable parameters.


enhancing-generalization-of-vision-language-models-through-efficient-prompt-tuning-with-dense-information


Enhancing Generalization of Vision-Language Models through Efficient Prompt Tuning with Dense Information
