mlsanityData to 7 Oct 2026

Distribution-aware Margin Calibration for Semantic Segmentation in Images

arXiv 2112.11554 ↗First posted 21 Dec 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable. Although some algorithms have been proposed to optimize its surrogates, there is no guarantee provided for the generalization ability. In this paper, we propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution, underpinned by a rigid lower bound. This scheme theoretically ensures a better segmentation performance in terms of IoU score. We evaluated the effectiveness of the proposed margin calibration method on seven image datasets, showing substantial improvements in IoU score over other learning objectives using deep segmentation models.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 73 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

35 of 73 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  11. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  12. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
23 more
  1. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  2. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  3. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  5. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  6. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  7. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  8. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  9. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 226
  10. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  11. 2018Boundary loss for highly unbalanced segmentationcited by 187
  12. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 171
  13. 20192017 Robotic Instrument Segmentation Challengecited by 166
  14. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  15. 2019Striking the Right Balance with Uncertaintycited by 79
  16. 2020Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networkscited by 70
  17. 2020Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Indexcited by 52
  18. 2018Adaptive Affinity Fields for Semantic Segmentationcited by 48
  19. 20183D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizescited by 42
  20. 2019Learning Surrogate Lossescited by 21
  21. 2019SPGNet: Semantic Prediction Guidance for Scene Parsingcited by 21
  22. 2019McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Boundscited by 15
  23. 2014Image processingcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 2.

4 papers.

  1. 2024Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methodscited by 8
  2. 2022Self-attention on Multi-Shifted Windows for Scene Segmentationcited by 1
  3. 2025GRAPHITE: Graph-Based Interpretable Tissue Examination for Enhanced Explainability in Breast Cancer Histopathologycited by 1
  4. 2025Classifier Enhancement Using Extended Context and Domain Experts for Semantic Segmentationcited by 0