MixerCSeg：一种基于解耦 Mamba 注意力的高效裂缝分割混合器架构
MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention
TransMixer 把 Mamba 的潜变量注意力拆成局部纹理、全局依赖与序列上下文三条并行通路，配合方向引导边缘门控卷积，为细长/不规则结构（裂缝、血管、道路）的像素级分割提供了一个低算力（2.05 GFLOPs）可复用的编码器设计范式。
原文依据 a Direction-guided Edge Gated Convolution (DEGConv) that strengthens edge sensitivity under irregular crack geometries
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论特征编码器通过塑造细纹理与细结构的表征，在像素级裂缝分割中发挥关键作用。现有基于 CNN、Transformer 和 Mamba 的模型各自只捕获了所需空间或结构信息的一部分，在建模复杂裂缝模式时仍存在明显缺口。为此，本文提出 MixerCSeg，一种如同协同专家团队般设计的混合器架构：在单一编码器内，类 CNN 通路聚焦局部纹理，Transformer 风格通路捕获全局依赖，Mamba 式流建模序列上下文。MixerCSeg 的核心是 TransMixer，它挖掘 Mamba 的潜变量注意力行为，同时建立能够自然表达局部性与全局感知的专用通路。为进一步提升结构保真度，本文引入空间块处理策略与方向引导边缘门控卷积（DEGConv），以极小的计算开销增强不规则裂缝几何下的边缘敏感性。随后采用空间细化多级融合（SRF）模块，在不增加复杂度的前提下细化多尺度细节。在多个裂缝分割基准上的大量实验表明，MixerCSeg 仅以 2.05 GFLOPs 和 2.54 M 参数即达到最优性能，兼具高效性与强表征能力。代码已开源：https://github.com/spiderforest/MixerCSeg。
英文原文摘要 1476 字符
Feature encoders play a key role in pixel-level crack segmentation by shaping the representation of fine textures and thin structures. Existing CNN-, Transformer-, and Mamba-based models each capture only part of the required spatial or structural information, leaving clear gaps in modeling complex crack patterns. To address this, we present MixerCSeg, a mixer architecture designed like a coordinated team of specialists, where CNN-like pathways focus on local textures, Transformer-style paths capture global dependencies, and Mamba-inspired flows model sequential context within a single encoder. At the core of MixerCSeg is the TransMixer, which explores Mamba's latent attention behavior while establishing dedicated pathways that naturally express both locality and global awareness. To further enhance structural fidelity, we introduce a spatial block processing strategy and a Direction-guided Edge Gated Convolution (DEGConv) that strengthens edge sensitivity under irregular crack geometries with minimal computational overhead. A Spatial Refinement Multi-Level Fusion (SRF) module is then employed to refine multi-scale details without increasing complexity. Extensive experiments on multiple crack segmentation benchmarks show that MixerCSeg achieves state-of-the-art performance with only 2.05 GFLOPs and 2.54 M parameters, demonstrating both efficiency and strong representational capability. The code is available at https://github.com/spiderforest/MixerCSeg.