Viet-Anh on Software Logo

What is: Channel-wise Cross Fusion Transformer?

SourceUCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Channel-wise Cross Fusion Transformer is a module used in the UCTransNet architecture for semantic segmentation. It fuses the multi-scale encoder features with the advantage of the long dependency modeling in the Transformer. The CCT module consists of three steps: multi-scale feature embedding, multi-head channel-wise cross attention and Multi-Layer Perceptron (MLP).