About initialization and visualization of group tokens

[o0t1ng0o]

Hi, @xvjiarui @shalinidemello
Thank you for presenting this good work.

I have some questions about the group tokens.
It seems that group_token is set as None for initialization in line 839 ./models/group_vit.py.
So how to make the group_token learnable? Why do not set it as a learnable parameters?

What's more, how do we get the segmentation mask through the model? It seems that the "class GroupViT" of ./models/group_vit.py only return the image features?

These make me very confused.
Could you please help me to solve my confusion?

[xvjiarui]

Hi @o0t1ng0o

Sorry for the late reply.
The group token is initialized here.

You may refer to this file for how to get the segmentation mask.