search

Omid-Nejati / BEFUnet

A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation
MIT License
38 stars 5 forks source link

CrossAttention And Self-Attention #3

Open daichuangye opened 3 months ago

daichuangye commented 3 months ago

Hello Author： In the CrossAttention class in the utils.py file, there is only one input parameter x, which actually computes Self-Attention. Is your code inconsistent with the content of your paper?

PANHAOC commented 1 month ago

I have the same question. I can't find the definition of the Local Cross-Attention Fusion module mentioned in the paper. In the forward, I only see the simple addition of convolutional features and swin features. Can you explain it?