EDMB: Edge Detector with Mamba

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Yachuan, Poma, Xavier Soria, Bai, Yun, Xiao, Qian, Yang, Chaozhi, Li, Guanlin, Li, Zongmin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915095594926080
author Li, Yachuan
Poma, Xavier Soria
Bai, Yun
Xiao, Qian
Yang, Chaozhi
Li, Guanlin
Li, Zongmin
author_facet Li, Yachuan
Poma, Xavier Soria
Bai, Yun
Xiao, Qian
Yang, Chaozhi
Li, Guanlin
Li, Zongmin
contents Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba have shown excellent ability in efficiently capturing long-range dependencies. Drawing inspiration from this, we propose a novel edge detector with Mamba, termed EDMB, to efficiently generate high-quality multi-granularity edges. In EDMB, Mamba is combined with a global-local architecture, therefore it can focus on both global information and fine-grained cues. The fine-grained cues play a crucial role in edge detection, but are usually ignored by ordinary Mamba. We design a novel decoder to construct learnable Gaussian distributions by fusing global features and fine-grained features. And the multi-grained edges are generated by sampling from the distributions. In order to make multi-granularity edges applicable to single-label data, we introduce Evidence Lower Bound loss to supervise the learning of the distributions. On the multi-label dataset BSDS500, our proposed EDMB achieves competitive single-granularity ODS 0.837 and multi-granularity ODS 0.851 without multi-scale test or extra PASCAL-VOC data. Remarkably, EDMB can be extended to single-label datasets such as NYUDv2 and BIPED. The source code is available at https://github.com/Li-yachuan/EDMB.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04846
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EDMB: Edge Detector with Mamba
Li, Yachuan
Poma, Xavier Soria
Bai, Yun
Xiao, Qian
Yang, Chaozhi
Li, Guanlin
Li, Zongmin
Computer Vision and Pattern Recognition
Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba have shown excellent ability in efficiently capturing long-range dependencies. Drawing inspiration from this, we propose a novel edge detector with Mamba, termed EDMB, to efficiently generate high-quality multi-granularity edges. In EDMB, Mamba is combined with a global-local architecture, therefore it can focus on both global information and fine-grained cues. The fine-grained cues play a crucial role in edge detection, but are usually ignored by ordinary Mamba. We design a novel decoder to construct learnable Gaussian distributions by fusing global features and fine-grained features. And the multi-grained edges are generated by sampling from the distributions. In order to make multi-granularity edges applicable to single-label data, we introduce Evidence Lower Bound loss to supervise the learning of the distributions. On the multi-label dataset BSDS500, our proposed EDMB achieves competitive single-granularity ODS 0.837 and multi-granularity ODS 0.851 without multi-scale test or extra PASCAL-VOC data. Remarkably, EDMB can be extended to single-label datasets such as NYUDv2 and BIPED. The source code is available at https://github.com/Li-yachuan/EDMB.
title EDMB: Edge Detector with Mamba
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.04846