rishikksh20 / ResUnet

Pytorch implementation of ResUnet and ResUnet ++

Repository from Github https://github.comrishikksh20/ResUnetRepository from Github https://github.comrishikksh20/ResUnet

Attention block

JanPalasek opened this issue · comments

Hi, could you please explain where you got the implementation for your attention block? I've studied papers reference to global attention unit in semantic segmentation ([31] https://arxiv.org/pdf/1805.10180.pdf - Pyramid Attention Network
for Semantic Segmentation) and also ([30] https://arxiv.org/pdf/1706.03762.pdf - Attention Is All You Need) and your implementation is significantly different.

Contacted the authors, it seems to be the correct implementation.