Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network

Fuzhang Li, Chuan Lin

TL;DR

UHNet addresses the need for fast, resource-efficient edge detection suitable for medical imaging and edge devices. It introduces the ultra-lightweight PDDP feature extraction block and a compact backbone with pooled residual connections and lightweight feature fusion, achieving minimal parameter count with high throughput. The three-branch architecture is validated on BSDS500, NYUD, and BIPED, delivering 42.3k parameters, 166 FPS, and 0.79G FLOPs while maintaining competitive edge-detection accuracy. The work demonstrates the practicality of ultra-lightweight designs for real-time medical image analysis and provides open-source code for broader adoption.

Abstract

Edge detection is crucial in medical image processing, enabling precise extraction of structural information to support lesion identification and image analysis. Traditional edge detection models typically rely on complex Convolutional Neural Networks and Vision Transformer architectures. Due to their numerous parameters and high computational demands, these models are limited in their application on resource-constrained devices. This paper presents an ultra-lightweight edge detection model (UHNet), characterized by its minimal parameter count, rapid computation speed, negligible of pre-training costs, and commendable performance. UHNet boasts impressive performance metrics with 42.3k parameters, 166 FPS, and 0.79G FLOPs. By employing an innovative feature extraction module and optimized residual connection method, UHNet significantly reduces model complexity and computational requirements. Additionally, a lightweight feature fusion strategy is explored, enhancing detection accuracy. Experimental results on the BSDS500, NYUD, and BIPED datasets validate that UHNet achieves remarkable edge detection performance while maintaining high efficiency. This work not only provides new insights into the design of lightweight edge detection models but also demonstrates the potential and application prospects of the UHNet model in engineering applications such as medical image processing. The codes are available at https://github.com/stoneLi20cv/UHNet

UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network

TL;DR

UHNet addresses the need for fast, resource-efficient edge detection suitable for medical imaging and edge devices. It introduces the ultra-lightweight PDDP feature extraction block and a compact backbone with pooled residual connections and lightweight feature fusion, achieving minimal parameter count with high throughput. The three-branch architecture is validated on BSDS500, NYUD, and BIPED, delivering 42.3k parameters, 166 FPS, and 0.79G FLOPs while maintaining competitive edge-detection accuracy. The work demonstrates the practicality of ultra-lightweight designs for real-time medical image analysis and provides open-source code for broader adoption.

Abstract

Edge detection is crucial in medical image processing, enabling precise extraction of structural information to support lesion identification and image analysis. Traditional edge detection models typically rely on complex Convolutional Neural Networks and Vision Transformer architectures. Due to their numerous parameters and high computational demands, these models are limited in their application on resource-constrained devices. This paper presents an ultra-lightweight edge detection model (UHNet), characterized by its minimal parameter count, rapid computation speed, negligible of pre-training costs, and commendable performance. UHNet boasts impressive performance metrics with 42.3k parameters, 166 FPS, and 0.79G FLOPs. By employing an innovative feature extraction module and optimized residual connection method, UHNet significantly reduces model complexity and computational requirements. Additionally, a lightweight feature fusion strategy is explored, enhancing detection accuracy. Experimental results on the BSDS500, NYUD, and BIPED datasets validate that UHNet achieves remarkable edge detection performance while maintaining high efficiency. This work not only provides new insights into the design of lightweight edge detection models but also demonstrates the potential and application prospects of the UHNet model in engineering applications such as medical image processing. The codes are available at https://github.com/stoneLi20cv/UHNet
Paper Structure (10 sections, 5 figures, 6 tables)

This paper contains 10 sections, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. PDDP Block
  5. UHNet Architecture
  6. Experiment
  7. Experimental Details
  8. Ablation Study
  9. Comparison with Other Models
  10. Conclusion and Discussion

Figures (5)

  • Figure 1: (a) Bottleneck structure in ResNet he2016deep; (b) Lightweight Bottleneck structure; (c) PDDP block.
  • Figure 2: UHNet Architecture.
  • Figure 3: Performance comparison between two 3×3 depthwise convolution kernels and one 5×5 depthwise convolution kernel in the PDDP block.
  • Figure 4: Comparison analysis of Shortcut 1×1 and PoolBlock.
  • Figure 5: Qualitative comparison of the UHNet series models with other methods.