EDMB: Edge Detector with Mamba

TL;DR

EDMB is a novel edge detection method that combines Mamba with a global-local architecture and a specialized decoder to efficiently generate high-quality multi-granularity edges, outperforming existing models on key datasets.

Contribution

This paper introduces EDMB, a new edge detector utilizing Mamba and a learnable Gaussian distribution-based decoder for multi-granularity edge detection.

Findings

Achieves competitive ODS scores on BSDS500 without multi-scale testing.

Extends effectively to single-label datasets like NYUDv2 and BIPED.

Operates efficiently with high-quality results.

Abstract

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.