search

BeierZhu / xERM

[AAAI 2022 Oral] This is a Pytorch implementation of the AAAI 2022 paper "Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification"
33 stars 7 forks source link

xERM-TDE ImageNet Performance #1

Closed zuglerQ closed 1 year ago

zuglerQ commented 2 years ago

Dear Beier, Thank you for your innovative work and I am really interested in it. However, when training the ImageNet_LT dataset with xERM-TDE method, I got low performance only 14.4 in the overall accuracy. I would like to ask, is it convenient to share the ImageNet_LT training code or configs there to make sure we could get your sota results?

BeierZhu commented 2 years ago

Hello, the training code for ImageNet_LT on xERM-TDE will be updated after ECCV deadline.

zuglerQ commented 2 years ago

Thank you for your reply. I am looking forward to the updated code.

BeierZhu commented 1 year ago

https://drive.google.com/file/d/1SZ9g-03Jn31o-iFySTHb_Z8dSRxEsV8G/view?usp=sharing

Hi, I don't have time to clean up the code and write readme for the rest datasets and backbones. I just zip all the code for xERM-TDE. You can refer to the xERM-PC to reproduce the results of xERM-TDE.