The difference between strong_baseline and MMT proposed in unsupervised domain adaptation

open-mmlab / OpenUnReID

PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.

Apache License 2.0

397 stars 67 forks source link

The difference between strong_baseline and MMT proposed in unsupervised domain adaptation #22

Open GJTNB opened 4 years ago

GJTNB commented 4 years ago

I see that this benchmark network is from sec3.1 in the MMT paper. How is it trained? Does it require collaborative training?

yxgeee commented 4 years ago

It does not require collaborative training. Only one network is used for training, supervised by a cross-entropy loss and a triplet loss.

GJTNB commented 4 years ago

Do you use clustering? Are there any techniques in clustering? Or is this benchmark based on that paper?

yxgeee commented 3 years ago

Yes, clustering is used for generating pseudo labels. Please refer to the code for the details. If you understand Chinese, you could also refer to https://apposcmf8kb5033.h5.xeknow.com/st/9k0kMekYC, where I have mentioned the architectures of this codebase, as well as the strong baseline design.