Topology-aware Mamba for Crack Segmentation in Structures

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zuo, Xin, Sheng, Yu, Shen, Jifeng, Shan, Yongwei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914992043851776
author Zuo, Xin
Sheng, Yu
Shen, Jifeng
Shan, Yongwei
author_facet Zuo, Xin
Sheng, Yu
Shen, Jifeng
Shan, Yongwei
contents CrackMamba, a Mamba-based model, is designed for efficient and accurate crack segmentation for monitoring the structural health of infrastructure. Traditional Convolutional Neural Network (CNN) models struggle with limited receptive fields, and while Vision Transformers (ViT) improve segmentation accuracy, they are computationally intensive. CrackMamba addresses these challenges by utilizing the VMambaV2 with pre-trained ImageNet-1k weights as the encoder and a newly designed decoder for better performance. To handle the random and complex nature of crack development, a Snake Scan module is proposed to reshape crack feature sequences, enhancing feature extraction. Additionally, the three-branch Snake Conv VSS (SCVSS) block is proposed to target cracks more effectively. Experiments show that CrackMamba achieves state-of-the-art (SOTA) performance on the CrackSeg9k and SewerCrack datasets, and demonstrates competitive performance on the retinal vessel segmentation dataset CHASE\underline{~}DB1, highlighting its generalization capability. The code is publicly available at: {https://github.com/shengyu27/CrackMamba.}
format Preprint
id arxiv_https___arxiv_org_abs_2410_19894
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Topology-aware Mamba for Crack Segmentation in Structures
Zuo, Xin
Sheng, Yu
Shen, Jifeng
Shan, Yongwei
Computer Vision and Pattern Recognition
CrackMamba, a Mamba-based model, is designed for efficient and accurate crack segmentation for monitoring the structural health of infrastructure. Traditional Convolutional Neural Network (CNN) models struggle with limited receptive fields, and while Vision Transformers (ViT) improve segmentation accuracy, they are computationally intensive. CrackMamba addresses these challenges by utilizing the VMambaV2 with pre-trained ImageNet-1k weights as the encoder and a newly designed decoder for better performance. To handle the random and complex nature of crack development, a Snake Scan module is proposed to reshape crack feature sequences, enhancing feature extraction. Additionally, the three-branch Snake Conv VSS (SCVSS) block is proposed to target cracks more effectively. Experiments show that CrackMamba achieves state-of-the-art (SOTA) performance on the CrackSeg9k and SewerCrack datasets, and demonstrates competitive performance on the retinal vessel segmentation dataset CHASE\underline{~}DB1, highlighting its generalization capability. The code is publicly available at: {https://github.com/shengyu27/CrackMamba.}
title Topology-aware Mamba for Crack Segmentation in Structures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.19894