Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision

Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas

TL;DR

This work proposes \MethodLPP, a lightweight, only $\sim$21K additional parameters, and plug-and-play matching-based supervision module that can be appended to any edge detection model for joint end-to-end learning of crisp edges, and substantially improves the performance of existing edge detection models.

Abstract

Generating crisp, i.e., one-pixel-wide, edge maps remains one of the fundamental challenges in edge detection, affecting both traditional and learning-based methods. To obtain crisp edges, most existing approaches rely on two hand-crafted post-processing algorithms, Non-Maximum Suppression (NMS) and skeleton-based thinning, which are non-differentiable and hinder end-to-end optimization. Moreover, all existing crisp edge detection methods still depend on such post-processing to achieve satisfactory results. To address this limitation, we propose \MethodLPP, a lightweight, only $\sim$21K additional parameters, and plug-and-play matching-based supervision module that can be appended to any edge detection model for joint end-to-end learning of crisp edges. At each training iteration, \MethodLPP performs one-to-one matching between predicted and ground-truth edges based on spatial distance and confidence, ensuring consistency between training and testing protocols. Extensive experiments on four popular datasets demonstrate that integrating \MethodLPP substantially improves the performance of existing edge detection models. In particular, \MethodLPP increases the Average Crispness (AC) metric by up to 2--4$\times$ compared to baseline models. Under the crispness-emphasized evaluation (CEval), \MethodLPP further boosts baseline performance by up to 20--35\% in ODS and achieves similar gains in OIS and AP, achieving SOTA performance that matches or surpasses standard post-processing for the first time. Code is available at https://cvpr26-matched.github.io.

MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision

TL;DR

This work proposes \MethodLPP, a lightweight, only 21K additional parameters, and plug-and-play matching-based supervision module that can be appended to any edge detection model for joint end-to-end learning of crisp edges, and substantially improves the performance of existing edge detection models.

Abstract

Generating crisp, i.e., one-pixel-wide, edge maps remains one of the fundamental challenges in edge detection, affecting both traditional and learning-based methods. To obtain crisp edges, most existing approaches rely on two hand-crafted post-processing algorithms, Non-Maximum Suppression (NMS) and skeleton-based thinning, which are non-differentiable and hinder end-to-end optimization. Moreover, all existing crisp edge detection methods still depend on such post-processing to achieve satisfactory results. To address this limitation, we propose \MethodLPP, a lightweight, only 21K additional parameters, and plug-and-play matching-based supervision module that can be appended to any edge detection model for joint end-to-end learning of crisp edges. At each training iteration, \MethodLPP performs one-to-one matching between predicted and ground-truth edges based on spatial distance and confidence, ensuring consistency between training and testing protocols. Extensive experiments on four popular datasets demonstrate that integrating \MethodLPP substantially improves the performance of existing edge detection models. In particular, \MethodLPP increases the Average Crispness (AC) metric by up to 2--4 compared to baseline models. Under the crispness-emphasized evaluation (CEval), \MethodLPP further boosts baseline performance by up to 20--35\% in ODS and achieves similar gains in OIS and AP, achieving SOTA performance that matches or surpasses standard post-processing for the first time. Code is available at https://cvpr26-matched.github.io.
Paper Structure (17 sections, 8 equations, 3 figures, 6 tables)

This paper contains 17 sections, 8 equations, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Standard Post-Processing in Edge Detection.
  4. Crisp Edge Detection.
  5. Methodology: MatchED
  6. Problem Definition and Notation
  7. Integrating MatchED into Existing Detectors
  8. Alignment & Matching with Ground Truth
  9. Training Objective
  10. Experiments
  11. Experimental Setup and Details
  12. Exp 1: Comparison w/ Crisp Edge Detectors
  13. Exp 2: Comparison w/ All Edge Detectors
  14. Exp 3: Ablation Analysis
  15. Exp 4: Efficiency Analysis
  16. ...and 2 more sections

Figures (3)

  • Figure 1: (a) Existing edge detectors require the use of a hand-crafted post-processing stage (e.g., NMS and thinning). (b) With MatchED, we generate a one-pixel-wide edge map in an end-to-end trainable manner. The recent DiffusionEdge's results ye2024diffusionedge(c) improve when integrated with MatchED(d).
  • Figure 2: An overview of MatchED, which can be easily integrated into any edge detector pipeline. A lightweight CNN consists of five blocks, each containing Conv2D, ReLU, and normalization layers, followed by a final Conv2D layer with a sigmoid activation. Therefore, MatchED adds only approximately 21K parameters.
  • Figure 3: Exp 5: Visual results of the raw outputs of SOTA models, their results after applying NMS, and their MatchED integrated versions on NYUD-v2 dataset. Best viewed by zooming in. Baseline results are generated from the pipeline of MatchED.