# MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention

arXiv: https://arxiv.org/abs/2603.01361 · HTML: https://mlsanity.com/paper/2603.01361/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [DeciMamba: Exploring the Length Extrapolation Potential of Mamba](https://mlsanity.com/paper/2406.14528/) (2024)
- [LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement](https://mlsanity.com/paper/2504.16053/) (2025)
- [Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers](https://mlsanity.com/paper/2503.11579/) (2025)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures](https://mlsanity.com/paper/2503.01113/) (2025)
- [A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation](https://mlsanity.com/paper/2303.01582/) (2023)
- [Topology-aware Mamba for Crack Segmentation in Structures](https://mlsanity.com/paper/2410.19894/) (2024)
- [An Efficient and Mixed Heterogeneous Model for Image Restoration](https://mlsanity.com/paper/2504.10967/) (2025)
- [Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection](https://mlsanity.com/paper/2109.05707/) (2021)

## Built on by (most cited first, 3 of 3)

- [Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling](https://mlsanity.com/paper/2605.31048/) (2026)
- [Rapid-Deployment Crack Measurement Based on SAM3 Semantic-Edge Response Decoding](https://mlsanity.com/paper/2607.12292/) (2026)
- [CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation](https://mlsanity.com/paper/2609.05816/) (2026)

## Abstract (arXiv)

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.