Closed slacklife closed 1 year ago
Hi @slacklife , thanks for checking out our work.
Hi, many thanks for your reply ! I still have another question want to figure out.
HFsoftmax is designed for massive classification and HFsoftmax's result is slightly lower than full softmax in table1 of paper. There are only about 8.6K identities in part0, not as many as 100K identities in full Celeb-1M and 672K identities in MegaFace. Why do you use hfsoftmax to train resnet50_part0_train.pth.tar instead of the full softmax or cos face(I found there is the cos face classifier implementation in hfsoftmax) ? These method maybe get a better result.
@slacklife You are right. Actually, to avoid interference from irrelevant factors, we use the full softmax for training instead of hfsoftmax and CosFace. To be more clear, we mentioned hfsoftmax here only to use the shared code for face recognition.
Another paper from our group, CDP, has studied the influence of models trained with different losses. It shows that better initial model often lead to better clustering results.
Hi, @slacklife Could you unzip the file “resnet50_part0_train.pth.tar”
Hi @houguanqun, please refer to the discussion of pretrained model in https://github.com/yl-1993/learn-to-cluster/issues/75.
Hi @yl-1993, really an amazing work! I have some questions about the dataset. In https://github.com/yl-1993/learn-to-cluster/blob/master/DATASET.md
Thanks!