mlsanityData to 14 Oct 2026

RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses

arXiv 2403.01795 ↗First posted 4 Mar 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators. Existing solutions address P1 using class-balanced cross-entropy loss and dice loss and P2 by only predicting edges agreed upon by most annotators. In this paper, we propose RankED, a unified ranking-based approach that addresses both the imbalance problem (P1) and the uncertainty problem (P2). RankED tackles these two problems with two components: One component which ranks positive pixels over negative pixels, and the second which promotes high confidence edge pixels to have more label certainty. We show that RankED outperforms previous studies and sets a new state-of-the-art on NYUD-v2, BSDS500 and Multi-cue datasets. Code is available at https://ranked-cvpr24.github.io.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

32 of 54 references.

References · 32

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  3. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  4. 2015Holistically-Nested Edge Detectioncited by 592
  5. 2021Deep Long-Tailed Learning: A Surveycited by 417
  6. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  7. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  8. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 168
  9. 2016Richer Convolutional Features for Edge Detectioncited by 143
  10. 2019Imbalance Problems in Object Detection: A Reviewcited by 118
  11. 2018Learning to predict crisp boundariescited by 82
  12. 2019Bi-Directional Cascade Network for Perceptual Edge Detectioncited by 72
20 more
  1. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  2. 2014Fast Edge Detection Using Structured Forestscited by 65
  3. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  4. 2014DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detectioncited by 50
  5. 2018Efficient Uncertainty Estimation for Semantic Segmentation in Videoscited by 46
  6. 2019Towards Accurate One-Stage Object Detection with AP-Losscited by 36
  7. 2019Uncertainty Estimation in One-Stage Object Detectioncited by 36
  8. 2015Pushing the Boundaries of Boundary Detection using Deep Learningcited by 35
  9. 2016Object Contour Detection with a Fully Convolutional Encoder-Decoder Networkcited by 34
  10. 2021RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depthcited by 33
  11. 2018Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Predictioncited by 30
  12. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  13. 2014Oriented Edge Forests for Boundary Detectioncited by 25
  14. 2020A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detectioncited by 25
  15. 2023The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detectorcited by 25
  16. 2015High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Visioncited by 24
  17. 2019DR Loss: Improving Object Detection by Distributional Rankingcited by 24
  18. 2020AP-Loss for Accurate One-Stage Object Detectioncited by 24
  19. 2021Rank & Sort Loss for Object Detection and Instance Segmentationcited by 22
  20. 2019Object Contour and Edge Detection with RefineContourNetcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 10; 2026: 4.

19 papers.

Sort:

By area:

  1. 2025U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detectioncited by 12
  2. 2024SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detectioncited by 7
  3. 2024Generative Edge Detection with Stable Diffusioncited by 5
  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. 2025EDMB: Edge Detector with Mambacited by 2
  7. 2025Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detectioncited by 2
  8. 2024Learning to utilize image second-order derivative information for crisp edge detectioncited by 1
  9. 2024EDCSSM: Edge Detection with Convolutional State Space Modelcited by 1
  10. 2025Improving Transformer Based Line Segment Detection with Matched Predicting and Re-rankingcited by 1
  11. 2025Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detectioncited by 1
  12. 2025Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detectioncited by 1
7 more
  1. 2026MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervisioncited by 1
  2. 2025FG 2025 TrustFAA: the First Workshop on Towards Trustworthy Facial Affect Analysis: Advancing Insights of Fairness, Explainability, and Safety (TrustFAA)cited by 0
  3. 2025Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detectioncited by 0
  4. 2025MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNscited by 0
  5. 2026A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classificationcited by 0
  6. 2026R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inferencecited by 0
  7. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0