UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer

🤖 Plain-English Summary

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the advanced for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework.

🔑 Key Findings

• It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets.
• Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism.
• Specifically, the CTrans (Channel Transformer) module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity.

🔗 Related Resources