# STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization

arXiv: https://arxiv.org/abs/2201.05121 · HTML: https://mlsanity.com/paper/2201.05121/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 75 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning](https://mlsanity.com/paper/1909.01804/) (2019)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow](https://mlsanity.com/paper/1501.02565/) (2015)
- [Bi-Directional Cascade Network for Perceptual Edge Detection](https://mlsanity.com/paper/1902.10903/) (2019)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [Making Risk Minimization Tolerant to Label Noise](https://mlsanity.com/paper/1403.3610/) (2014)
- [DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection](https://mlsanity.com/paper/1412.1123/) (2014)
- [Structured Consistency Loss for semi-supervised semantic segmentation](https://mlsanity.com/paper/2001.04647/) (2020)
- [Semi-Supervised Semantic Image Segmentation with Self-correcting Networks](https://mlsanity.com/paper/1811.07073/) (2018)
- [Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation](https://mlsanity.com/paper/1907.10303/) (2019)
- [Improving Semantic Segmentation via Self-Training](https://mlsanity.com/paper/2004.14960/) (2020)
- [Oriented Edge Forests for Boundary Detection](https://mlsanity.com/paper/1412.4181/) (2014)
- [SCORES: Shape Composition with Recursive Substructure Priors](https://mlsanity.com/paper/1809.05398/) (2018)
- [Unsupervised Learning of Edges](https://mlsanity.com/paper/1511.04166/) (2015)
- [FINED: Fast Inference Network for Edge Detection](https://mlsanity.com/paper/2012.08392/) (2020)

## Built on by (most cited first, 2 of 2)

- [HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly](https://mlsanity.com/paper/2507.19924/) (2025)
- [SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection](https://mlsanity.com/paper/2401.02313/) (2024)

## Abstract (arXiv)

Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale unlabeled image datasets. We design a self-supervised framework with multi-layer regularization and self-teaching. In particular, we impose a consistency regularization which enforces the outputs from each of the multiple layers to be consistent for the input image and its perturbed counterpart. We adopt L0-smoothing as the 'perturbation' to encourage edge prediction lying on salient boundaries following the cluster assumption in self-supervised learning. Meanwhile, the network is trained with multi-layer supervision by pseudo labels which are initialized with Canny edges and then iteratively refined by the network as the training proceeds. The regularization and self-teaching together attain a good balance of precision and recall, leading to a significant performance boost over supervised methods, with lightweight refinement on the target dataset. Furthermore, our method demonstrates strong cross-dataset generality. For example, it attains 4.8% improvement for ODS and 5.8% for OIS when tested on the unseen BIPED dataset, compared to the state-of-the-art methods.