search

tfzhou / ProtoSeg

CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View
https://arxiv.org/abs/2203.15102
MIT License
341 stars 38 forks source link

Layernorm in Prototype learning #12

Open Trainingzy opened 1 year ago

Trainingzy commented 1 year ago

Thanks for your great work! I notice you use layernorm for the final features before the classifier and also for the predictions. I think it is quite uncommon in prototype learning (correct me if i am wrong).

Could you please provide some explanation for this? And if removing the two layernorm, will the performance be degraded?

https://github.com/tfzhou/ProtoSeg/blob/1c4a7784bbce96c06fe72d55255af15e6cf1ca96/lib/models/nets/hrnet.py#L81

kaigelee commented 11 months ago

Have you solved it? I have the same problem