mlsanityData to 7 Oct 2026

Unmixing Convolutional Features for Crisp Edge Detection

arXiv 2011.09808 ↗First posted 19 Nov 2020cs.CVcited by 32

Not on the map. Why?

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.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 5; 2024: 10; 2025: 5; 2026: 5.

32 papers.

Sort:

By area:

  1. 2021Dense Extreme Inception Network for Edge Detectioncited by 37
  2. 2024DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detectioncited by 33
  3. 2023Tiny and Efficient Model for the Edge Detection Generalizationcited by 28
  4. 2022Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learningcited by 26
  5. 2024OmniControlNet: Dual-stage Integration for Conditional Image Generationcited by 24
  6. 2022ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priorscited by 21
  7. 2023Delving into Crispness: Guided Label Refinement for Crisp Edge Detectioncited by 10
  8. 2021Learning Deep Morphological Networks with Neural Architecture Searchcited by 6
  9. 2021'CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networkscited by 5
  10. 2022One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learningcited by 5
  11. 2024Generative Edge Detection with Stable Diffusioncited by 5
  12. 2025ScaleLSD: Scalable Deep Line Segment Detection Streamlinedcited by 5
20 more
  1. 2021The magnitude vector of imagescited by 4
  2. 2024Cycle Pixel Difference Network for Crisp Edge Detectioncited by 3
  3. 2024Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Imagescited by 3
  4. 2025Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigmcited by 3
  5. 2024A Comprehensive Study for Edge Detection: Ideal-Prior Guidance Learning, High-Precision Architecture, and Better Distinguishability Evaluation Benchmarkcited by 2
  6. 2025Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detectioncited by 2
  7. 2024Learning to utilize image second-order derivative information for crisp edge detectioncited by 1
  8. 2024A new baseline for edge detection: Make Encoder-Decoder great againcited by 1
  9. 2025Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detectioncited by 1
  10. 2026MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervisioncited by 1
  11. 2026MEMO: Human-like Crisp Edge Detection Using Masked Edge Predictioncited by 1
  12. 2023Compact Twice Fusion Network for Edge Detectioncited by 0
  13. 2023DeNISE: Deep Networks for Improved Segmentation Edgescited by 0
  14. 2023Holistic Geometric Feature Learning for Structured Reconstructioncited by 0
  15. 2024Msmsfnet: a multi-stream and multi-scale fusion net for edge detectioncited by 0
  16. 2024UHNet: An Ultra-Lightweight and High-Speed Edge Detection Networkcited by 0
  17. 2025Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detectioncited by 0
  18. 2026EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detectioncited by 0
  19. 2026Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Modelscited by 0
  20. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0