search

tinyvision / SOLIDER

A Semantic Controllable Self-Supervised Learning Framework to learn general human representations from massive unlabeled human images, which can benefit downstream human-centric tasks to the maximum extent
Apache License 2.0
1.92k stars 347 forks source link

Visualize and manually modify semantic clustering #14

Open ikergf opened 1 year ago

ikergf commented 1 year ago

Hello,

I was wondering if it is possible to visualize the semantic clustering results of the input images (and the attention maps) as in your paper. I have tried it, but I have not been able to visualize them.

Moreover, I was also thinking about modifying the clustering masks with my own ones so the model could learn to focus on the specified parts, but I'm having some problems. Do you think it is feasible?

cwhgn commented 1 year ago

You can modify the following function to implement the visualization. https://github.com/tinyvision/SOLIDER/blob/b8779cc5cfaa7d44b277e8305bc42bce377fe8c0/utils.py#L658