Train model with ground truth label.

chenhao2345 / ICE

Implementation for ICCV 2021 paper "ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification"

MIT License

44 stars 15 forks source link

Train model with ground truth label. #13

Open jjunnii opened 2 years ago

jjunnii commented 2 years ago

Hi, I am a graduate student who is conducting an experiment because I was impressed by your ICE model. If I want to check the performance of ICE model's Supervised model, should I use cross-camera loss (Camloss)?

chenhao2345 commented 2 years ago

Hi. Yes, you should keep the cross-camera loss. You only need to change the pseudo labels to real labels and keep all the losses.