search

zxhuang1698 / interpretability-by-parts

Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
https://www.biostat.wisc.edu/~yli/cvpr2020-interp/
128 stars 27 forks source link

Implementation on CUB dataset #4

Closed ShenghaiRong closed 4 years ago

ShenghaiRong commented 4 years ago

Thanks for your great work. When I transplanted the code to the CUB task, I just got the 86.4% accuracy. :( Specifically, the linear classifier on celeb task is replaced with a single linear(2048, 200) coresponding with a cross entropy loss. And the backbone is Resnet101. The experiments also followed the implementation details in the paper. I wonder if there are still some differences between the reimplementation and the source code. And would you please release the code or reveal more training details on CUB dataset?

zxhuang1698 commented 4 years ago

Hi, thanks for your interest in our work. The code has been updated.