Vanixxz / MEDAF

[AAAI2024] Exploring Diverse Representations for Open Set Recognition
12 stars 0 forks source link

AUROC not good as in article #3

Closed xulaupuz closed 1 month ago

xulaupuz commented 1 month ago

Hello, I run the code with only datasets path changed. I run with 2 datasets for now, for svhn I got only about 0.75 auroc, and for tinyimagenet, I got around 0.55, a bit better than purely random choice. I tried changing seeds, using another optimizer intergrated, configging learning rate, etc. And get almost same result said above. Any suggestions for me? Thanks.

Vanixxz commented 1 month ago

Thank you very much for your reminder. We apologize for uploading the incorrect version of the test code, which has been corrected. The updated code can now reproduce results as described in the paper.