Closed aniki-ly closed 2 years ago
Hi, thanks for your interest in our work. It seems a bug since the class embedding is used two times. We did not directly use the class embedding for dense prediction tasks so I think the final results might be affected significantly (we can even remove the class embedding during finetuning).
Thanks!
Hi, Thanks for your work DenseCLIP.
I have some question about the CLIPVisionTransformer.
the x have both image feature and class embedding. However, the cls_pos are also added with class_embedding. I think there is some conflict with origin CLIP code, could you tell me the reason for this operation?