# Unsupervised Learning of Edges

arXiv: https://arxiv.org/abs/1511.04166 · HTML: https://mlsanity.com/paper/1511.04166/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2015.

## Built on by (most cited first, 11 of 11)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Efficient Visual Pretraining with Contrastive Detection](https://mlsanity.com/paper/2103.10957/) (2021)
- [Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective](https://mlsanity.com/paper/2103.17263/) (2021)
- [Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2104.07917/) (2021)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)
- [STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization](https://mlsanity.com/paper/2201.05121/) (2022)
- [Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks](https://mlsanity.com/paper/2605.08320/) (2026)
- [Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization](https://mlsanity.com/paper/2606.10019/) (2026)
- [Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos](https://mlsanity.com/paper/2511.19936/) (2025)

## Abstract (arXiv)

Data-driven approaches for edge detection have proven effective and achieve top results on modern benchmarks. However, all current data-driven edge detectors require manual supervision for training in the form of hand-labeled region segments or object boundaries. Specifically, human annotators mark semantically meaningful edges which are subsequently used for training. Is this form of strong, high-level supervision actually necessary to learn to accurately detect edges? In this work we present a simple yet effective approach for training edge detectors without human supervision. To this end we utilize motion, and more specifically, the only input to our method is noisy semi-dense matches between frames. We begin with only a rudimentary knowledge of edges (in the form of image gradients), and alternate between improving motion estimation and edge detection in turn. Using a large corpus of video data, we show that edge detectors trained using our unsupervised scheme approach the performance of the same methods trained with full supervision (within 3-5%). Finally, we show that when using a deep network for the edge detector, our approach provides a novel pre-training scheme for object detection.