search

mousecpn / L2A-OT

This repository is an unofficial implementation in PyTorch for Learning to Generate Novel Domains for Domain Generalization
22 stars 4 forks source link

A question about person re-identification in domain generalization~ #1

Open soulredeem opened 3 years ago

soulredeem commented 3 years ago

For domain generalization, how could you train the model without same classes between only one source domain and target domain, like Market1501 and DukeMTMC-reID ? Could you release the code of person re-identification experiments？

mousecpn commented 3 years ago

I didn't reimplement the reID part, but the basic idea is replace the CE loss with triplet loss in some way.