frank-xwang / RIDE-LongTailRecognition

[ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."
MIT License
261 stars 26 forks source link

[Conceptual question] Are RIDE and EA used at the same time? #12

Closed Kouuh closed 3 years ago

Kouuh commented 3 years ago

Describe the error A clear and concise description of what your question is. I check that the loss used in the ride_ea.json configuration file is -CrossEntropyLoss. The loss used in the ride.json configuration file is RIDELoss. Therefore, the paper proposes that RIDELoss and EA Module can improve performance respectively. Rather than combining the two.

frank-xwang commented 3 years ago

Hi! Yes, the EA module is only applied in the second stage for reducing the overall computational cost.