yikaiw / CEN

[TPAMI 2023, NeurIPS 2020] Code release for "Deep Multimodal Fusion by Channel Exchanging"
MIT License
284 stars 43 forks source link

为什么对rgb, depth和ens的loss求和? #15

Closed ZqCATCAT closed 2 years ago

ZqCATCAT commented 2 years ago

作者你好!在文章的loss公式中,我的理解是只将ens拿来算loss。为什么代码里面需要对rgb,depth和ens的loss求和。

yikaiw commented 2 years ago

代码中分别对rgb,depth和ens的loss求和,主要为了解耦ens weight和网络的学习过程,即在更新ens weight时网络参数不更新。

https://github.com/yikaiw/CEN/blob/40f277ed1a377a3c81f979a6c534ae268773aa9d/semantic_segmentation/models/model.py#L316