# Unmixing Convolutional Features for Crisp Edge Detection

arXiv: https://arxiv.org/abs/2011.09808 · HTML: https://mlsanity.com/paper/2011.09808/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 30 of 32)

- [Dense Extreme Inception Network for Edge Detection](https://mlsanity.com/paper/2112.02250/) (2021)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [Tiny and Efficient Model for the Edge Detection Generalization](https://mlsanity.com/paper/2308.06468/) (2023)
- [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022)
- [OmniControlNet: Dual-stage Integration for Conditional Image Generation](https://mlsanity.com/paper/2406.05871/) (2024)
- [ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors](https://mlsanity.com/paper/2210.05950/) (2022)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- ['CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks](https://mlsanity.com/paper/2107.06212/) (2021)
- [One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning](https://mlsanity.com/paper/2203.09387/) (2022)
- [Generative Edge Detection with Stable Diffusion](https://mlsanity.com/paper/2410.03080/) (2024)
- [ScaleLSD: Scalable Deep Line Segment Detection Streamlined](https://mlsanity.com/paper/2506.09369/) (2025)
- [The magnitude vector of images](https://mlsanity.com/paper/2110.15188/) (2021)
- [Cycle Pixel Difference Network for Crisp Edge Detection](https://mlsanity.com/paper/2409.04272/) (2024)
- [Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images](https://mlsanity.com/paper/2410.06194/) (2024)
- [Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigm](https://mlsanity.com/paper/2501.02534/) (2025)
- [A Comprehensive Study for Edge Detection: Ideal-Prior Guidance Learning, High-Precision Architecture, and Better Distinguishability Evaluation Benchmark](https://mlsanity.com/paper/2407.19992/) (2024)
- [Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection](https://mlsanity.com/paper/2501.13365/) (2025)
- [Learning to utilize image second-order derivative information for crisp edge detection](https://mlsanity.com/paper/2406.05779/) (2024)
- [A new baseline for edge detection: Make Encoder-Decoder great again](https://mlsanity.com/paper/2409.14976/) (2024)
- [Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection](https://mlsanity.com/paper/2506.12460/) (2025)
- [MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision](https://mlsanity.com/paper/2602.20689/) (2026)
- [MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction](https://mlsanity.com/paper/2603.20782/) (2026)
- [Compact Twice Fusion Network for Edge Detection](https://mlsanity.com/paper/2307.04952/) (2023)
- [DeNISE: Deep Networks for Improved Segmentation Edges](https://mlsanity.com/paper/2309.02091/) (2023)
- [Holistic Geometric Feature Learning for Structured Reconstruction](https://mlsanity.com/paper/2309.09622/) (2023)
- [Msmsfnet: a multi-stream and multi-scale fusion net for edge detection](https://mlsanity.com/paper/2404.04856/) (2024)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)
- [Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection](https://mlsanity.com/paper/2507.06569/) (2025)
- [EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection](https://mlsanity.com/paper/2602.16238/) (2026)

## Abstract (arXiv)

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions. The CATS consists of two modules: a novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12% and 6% respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.