mlsanityData to 7 Oct 2026

Compensation Learning in Semantic Segmentation

arXiv 2304.13428 ↗First posted 26 Apr 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and several experiments demonstrate that our proposed compensation learns inter-class relations that allow global identification of challenging ambiguities as well as the exact localization of subsequent label noise. Additionally, it enlarges robustness against label noise during training and allows target-oriented manipulation during inference. We evaluate the proposed method on %the widely used datasets Cityscapes, KITTI-STEP, ADE20k, and COCO-stuff10k.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 74 of its 97 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

74 of 97 references.

References · 74

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
38 more
  1. 2019Searching for MobileNetV3cited by 1,984
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  4. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  5. 2018Panoptic Segmentationcited by 796
  6. 2018Image Transformercited by 770
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  8. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  9. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  10. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  12. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  13. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  14. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  15. 2019Panoptic-DeepLabcited by 362
  16. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  17. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  18. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  19. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  20. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  21. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  22. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  23. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  24. 2016One-Shot Video Object Segmentationcited by 233
  25. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  26. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  27. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  28. 2021K-Net: Towards Unified Image Segmentationcited by 211
  29. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  30. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  31. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  32. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  33. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  34. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  35. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  36. 2022Hyperbolic Image Segmentationcited by 101
  37. 2018Masking: A New Perspective of Noisy Supervisioncited by 93
  38. 2022Robust Training under Label Noise by Over-parameterizationcited by 93

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year

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

5 papers.

  1. 2023U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentationcited by 11
  2. 2023HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularizationcited by 9
  3. 2025UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Modelcited by 4
  4. 2024Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertaintycited by 3
  5. 2025NSegment : Label-specific Deformations for Remote Sensing Image Segmentationcited by 0