Open FYY799 opened 11 months ago
There are two main parts of the Mask Class Token. First one is that we add mask class token (by repeating the class token) to CLIP https://github.com/mlpc-ucsd/MaskCLIP/blob/43049d1d8465b2bfc3785df5d920d87df6e09579/maskclip/modeling/maskclip.py#L165-L168
Second one is that we use the segmentation masks to serve as attention mask in the self-attention layer https://github.com/mlpc-ucsd/MaskCLIP/blob/43049d1d8465b2bfc3785df5d920d87df6e09579/maskclip/modeling/maskclip.py#L50-L66.
Could you explain the code of Mask Class Token in the project?