UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network
Fuzhang Li, Chuan Lin

TL;DR
UHNet is a highly efficient, ultra-lightweight edge detection network designed for resource-constrained devices, achieving high speed and accuracy with minimal parameters and computational cost.
Contribution
The paper introduces UHNet, a novel lightweight edge detection model with innovative feature extraction and fusion strategies, significantly reducing complexity while maintaining high performance.
Findings
UHNet achieves 42.3k parameters and 166 FPS.
It demonstrates high accuracy on multiple datasets.
The model requires only 0.79G FLOPs.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCCD and CMOS Imaging Sensors · Advanced Computing and Algorithms · Image and Video Quality Assessment
MethodsAttention Is All You Need · Linear Layer · Multi-Head Attention · Position-Wise Feed-Forward Layer · Adam · Byte Pair Encoding · Softmax · Absolute Position Encodings · Vision Transformer · Dense Connections
