xyutao/fscil

Related to base class performances

Opened this issue · 1 comments

I have taken 100 CUB classes as base classes and learned the restnet-18 network. I followed the same setting (50 epochs) mentioned in paper and It is giving 69% as base task accuracy. But when I started with the same base classes using the NCM method (UCIR- where cosine normalization is applied on class weights and features are l2 normalized) the base task performance is giving around 74%. In the paper, base task performance is mentioned as 68.8% in both methods. Can you explain how it is possible? or any different training setting is needed for the NCM method for base class training?

Thank you.

Hello, I'm also interested in this work and would like to do some entry-level research. But since the files are missing and cannot be started, please ask if you have these missing files:
tools.ng_anchor ;
tools.loss ;
tools.plot ;
Please provide me with some ideas and have a good life!