diff --git a/Paper/CLIP/Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models.md b/Paper/CLIP/Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models.md index 7e158e7..74ba3da 100644 --- a/Paper/CLIP/Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models.md +++ b/Paper/CLIP/Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models.md @@ -1,2 +1,4 @@ # TODO -- How to train encoder with the opposite modality frozen encoder? \ No newline at end of file +- How to train encoder with the opposite modality frozen encoder? +- How to generate high level prompt? +- Why add the category-agnostic vector as global prompt? \ No newline at end of file