search

hendrycks / outlier-exposure

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)
Apache License 2.0
541 stars 107 forks source link

After fine-tuning pre-trained WideResNet, the ID classification drops a lot? #20

Open lygjwy opened 2 years ago

lygjwy commented 2 years ago

Hello! Thank you for your excellent work. I have some questions about the implementation. When I change the train_loader_ood with shuffle = True and the ID classification drops a lot after finetuning the pre-trained WideResNet with lr 0.001 and weight_decay 0.0005. The fine-tuned WideResNet in Cifar10 has 88.59% test classification accuracy compared with 94.39%. Instead, you use a random offset to induce the randomness. Could you please clarify the reason for this operation? Thanks again!

QingyangZhang commented 1 year ago

I am curious about this, too.