ShihaoShao-GH/SuperGlobal

Understand the reordering network

Closed this issue · 2 comments

Hello, thank you for your excellent work, but I don’t quite understand the reordering network. Why should I choose max pooling and average pooling to refine features? What is its theoretical basis? Can you give some non-experimental explanations of interpretability?

There are still some method details that I don’t know very well. Can I use WeChat to communicate? My account: y18300084937

Sorry for the delay. I just reached you out at Wechat:)