mlsanityData to 7 Oct 2026

Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier

arXiv 2407.04036 ↗First posted 4 Jul 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Incorporating pixel contextual information is critical for accurate segmentation. In this paper, we show that an effective way to incorporate contextual information is through a patch-based classifier. This patch classifier is trained to identify classes present within an image region, which facilitates the elimination of distractors and enhances the classification of small object segments. Specifically, we introduce Multi-scale Patch-based Multi-label Classifier (MPMC), a novel plug-in module designed for existing semi-supervised segmentation (SSS) frameworks. MPMC offers patch-level supervision, enabling the discrimination of pixel regions of different classes within a patch. Furthermore, MPMC learns an adaptive pseudo-label weight, using patch-level classification to alleviate the impact of the teacher's noisy pseudo-label supervision the student. This lightweight module can be integrated into any SSS framework, significantly enhancing their performance. We demonstrate the efficacy of our proposed MPMC by integrating it into four SSS methodologies and improving them across two natural image and one medical segmentation dataset, notably improving the segmentation results of the baselines across all the three datasets.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 46 of its 70 references that are in the map. First posted on arXiv 4 Jul 2024.

Builds on

46 of 70 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  12. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
34 more
  1. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  2. 2020Asymmetric Loss For Multi-Label Classificationcited by 379
  3. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 378
  4. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  5. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  6. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 248
  7. 2014Learning with Pseudo-Ensemblescited by 241
  8. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  9. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  10. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  11. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  12. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
  13. 2015ParseNet: Looking Wider to See Bettercited by 176
  14. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  15. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  16. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  17. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  18. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  19. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  20. 2021Can multi-label classification networks know what they don't know?cited by 100
  21. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 99
  22. 2021A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentationcited by 79
  23. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  24. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  25. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
  26. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  27. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  28. 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
  29. 2018Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learningcited by 33
  30. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  31. 2016Co-localization with Category-Consistent Features and Geodesic Distance Propagationcited by 14
  32. 2019Weakly Labeling the Antarctic: The Penguin Colony Casecited by 12
  33. 2024Enabling Uncertainty Estimation in Iterative Neural Networkscited by 11
  34. 2021Self-Training with Differentiable Teachercited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 5.

12 papers.

  1. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
  2. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  3. 2025Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustnesscited by 3
  4. 2025Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspectivecited by 2
  5. 2024Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphologycited by 1
  6. 2025Knowledge Consultation for Semi-Supervised Semantic Segmentationcited by 1
  7. 2025What is the Added Value of UDA in the VFM Era?cited by 1
  8. 2026CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labelscited by 1
  9. 2026Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentationcited by 1
  10. 2026PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentationcited by 0
  11. 2026CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teacherscited by 0
  12. 2026When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labelingcited by 0