AI Paper Atlas

Research map / Detection and segmentation / CNN features

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

Zilong Zhao, Zhengming Ding, Pei Niu, Wenhao Sun, Feng Guo

CVPR 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TransMixer to the VMamba + Segformer baseline (ablation)baseline crack segmenter · DeepCrackmIoU: 0.8826 -> 0.9016Improved
add DEGConv on top of TransMixer (ablation)MixerCSeg · DeepCrackmIoU: 0.9016 -> 0.9097Improved
add SRF module replacing the Segformer decoder (ablation)MixerCSeg · DeepCrackmIoU: 0.9097 -> 0.9151Improved
add SRF module replacing the Segformer decoder (ablation)MixerCSeg · computational costFLOPs (G): 19.18 -> 2.05Improved
use TransMixer instead of MambaVision hybrid encoder (ablation)MixerCSeg · DeepCrackmIoU: 0.9020 -> 0.9151Improved
use TransMixer instead of RestorMixer hybrid encoder (ablation)MixerCSeg · CamCrack789OIS: 0.8206 -> 0.8202No clear effect
set global channel ratio gamma to 0.5 instead of 0.3, 0.7 or 0.9 (ablation)TransMixer · DeepCrackmIoU: 0.9098 (0.3) -> 0.9151 (0.5)Improved
use 8x8 DEGConv cell instead of 2x2 (ablation)DEGConv · DeepCrackmIoU: 0.9104 -> 0.9151Improved
use 180 direction bins instead of 9 (ablation)DEGConv · DeepCrackmIoU: 0.9067 -> 0.9151Improved
use 180 bins instead of 360 bins (ablation)DEGConv · DeepCrackmIoU: 0.9077 -> 0.9151Improved
build direction embedding from directional priors instead of ARConv predicted angles (ablation)DEGConv · DeepCrackmIoU: 0.9106 -> 0.9151Improved
MixerCSeg versus SCSegamba on Crack500MixerCSeg · Crack500mIoU: 0.7778 -> 0.7824Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy