# Traditional Method Inspired Deep Neural Network for Edge Detection

arXiv: https://arxiv.org/abs/2005.13862 · HTML: https://mlsanity.com/paper/2005.13862/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 6 of 6)

- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Tiny and Efficient Model for the Edge Detection Generalization](https://mlsanity.com/paper/2308.06468/) (2023)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [Identifying centres of interest in paintings using alignment and edge detection: Case studies on works by Luc Tuymans](https://mlsanity.com/paper/2101.00858/) (2021)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)
- [Hybrid Multi-Stage Learning Framework for Edge Detection: A Survey](https://mlsanity.com/paper/2503.21827/) (2025)

## Abstract (arXiv)

Recently, Deep-Neural-Network (DNN) based edge prediction is progressing fast. Although the DNN based schemes outperform the traditional edge detectors, they have much higher computational complexity. It could be that the DNN based edge detectors often adopt the neural net structures designed for high-level computer vision tasks, such as image segmentation and object recognition. Edge detection is a rather local and simple job, the over-complicated architecture and massive parameters may be unnecessary. Therefore, we propose a traditional method inspired framework to produce good edges with minimal complexity. We simplify the network architecture to include Feature Extractor, Enrichment, and Summarizer, which roughly correspond to gradient, low pass filter, and pixel connection in the traditional edge detection schemes. The proposed structure can effectively reduce the complexity and retain the edge prediction quality. Our TIN2 (Traditional Inspired Network) model has an accuracy higher than the recent BDCN2 (Bi-Directional Cascade Network) but with a smaller model.