mlsanityData to 14 Oct 2026

Semi-Supervised Semantic Segmentation via Marginal Contextual Information

arXiv 2308.13900 ↗First posted 26 Aug 2023cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the spatial correlation of labels in segmentation maps by grouping neighboring pixels and considering their pseudo labels collectively. With this contextual information, our method, named S4MC, increases the amount of unlabeled data used during training while maintaining the quality of the pseudo labels, all with negligible computational overhead. Through extensive experiments on standard benchmarks, we demonstrate that S4MC outperforms existing state-of-the-art semi-supervised learning approaches, offering a promising solution for reducing the cost of acquiring dense annotations. For example, S4MC achieves a 1.39 mIoU improvement over the prior art on PASCAL VOC 12 with 366 annotated images. The code to reproduce our experiments is available at https://s4mcontext.github.io/

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 26 Aug 2023.

Builds on

53 of 65 references.

References · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2023Segment Anythingcited by 8,234
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  11. 2015Fast R-CNNcited by 2,933
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
38 more
  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  3. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  4. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  5. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  7. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  8. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  9. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  10. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  11. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  12. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  13. 2020Rethinking Pre-training and Self-trainingcited by 352
  14. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 344
  15. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  16. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  17. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  18. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 274
  19. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  20. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  21. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  22. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
  23. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  24. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  25. 2018SpaceNet: A Remote Sensing Dataset and Challenge Seriescited by 179
  26. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  27. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  28. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  29. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  30. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 104
  31. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  32. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  33. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  34. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  35. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  36. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  37. 2017Real-time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNscited by 55
  38. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 1.

8 papers.

  1. 2024Noisy Annotations in Semantic Segmentationcited by 5
  2. 2024Robot Instance Segmentation with Few Annotations for Graspingcited by 4
  3. 2025WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIPcited by 3
  4. 2024Hysteresis Activation Function for Efficient Inferencecited by 2
  5. 2025Knowledge Consultation for Semi-Supervised Semantic Segmentationcited by 1
  6. 2025Benchmarking Adversarial Patch Selection and Locationcited by 1
  7. 2025R3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domaincited by 0
  8. 2026CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiographycited by 0