search

frank-xwang / RIDE-LongTailRecognition

[ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."
MIT License
257 stars 25 forks source link

How to understand Formula 13 and 14 in your paper? #32

Closed MRZHANG-1997 closed 2 years ago

MRZHANG-1997 commented 2 years ago

Describe the error A clear and concise description of what your question is. Thank you for your work in long-tailed recognition problem. Your work is excellent, and i want to use RIDE in my research file. However, i was confusion in understanding formula 13 and 14. For example, what do γ means? and How to compute it? as well as what do α means? and How to compute it?

TonyLianLong commented 2 years ago

Please have a look at our loss function implementation. You don't need to re-implement it yourself if you just want to use it: https://github.com/frank-xwang/RIDE-LongTailRecognition/blob/main/model/loss.py#L124

MRZHANG-1997 commented 2 years ago

Dear Tony,

Thank you very much for your help!

Sincerely your,

Sun

At 2022-06-18 12:21:03, "Long(Tony) Lian" @.***> wrote:

Please have a look at our loss function implementation. You don't need to re-implement it yourself if you just want to use it: https://github.com/frank-xwang/RIDE-LongTailRecognition/blob/main/model/loss.py#L124

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>