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

TLDR

Recent semantic‑segmentation methods rely on U‑Net, yet its simple skip connections struggle to capture global multi‑scale context, often producing incompatible feature sets and sometimes degrading performance. This work introduces UCTransNet, a U‑Net variant that rethinks skip connections through a channel‑wise attention mechanism. UCTransNet replaces conventional skip links with a CTrans module comprising a Channel‑Cross Transformer (CCT) for multi‑scale fusion and a Channel‑wise Cross‑Attention (CCA) sub‑module that guides fused channels to the decoder, resolving semantic gaps. Experiments show UCTransNet achieves more accurate segmentation and consistently outperforms state‑of‑the‑art methods across diverse datasets and backbone architectures. Code is available at https://github.com/McGregorWwww/UCTransNet.

Abstract

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. 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. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework. Code: https://github.com/McGregorWwww/UCTransNet.