mlsanityData to 7 Oct 2026

Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation

arXiv 2203.10196 ↗First posted 19 Mar 2022cs.CV cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consists of an encoder and a two-head decoders. One decoder learns positive attention to the foreground regions of interest (RoI) on unlabelled images thereby generating dilated features. The other decoder learns negative attention to the foreground on the same unlabelled images thereby generating eroded features. We then apply a consistency regularisation on the paired predictions. MisMatch outperforms state-of-the-art semi-supervised methods on a CT-based pulmonary vessel segmentation task and a MRI-based brain tumour segmentation task. In addition, we show that the effectiveness of MisMatch comes from better model calibration than its supervised learning counterpart.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

28 of 42 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  12. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
16 more
  1. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  2. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  3. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  4. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  5. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  6. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  7. 2018There Are Many Consistent Explanations of Unlabeled Data: Why You Should Averagecited by 82
  8. 2019Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentationcited by 55
  9. 2019Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Modelcited by 53
  10. 2018Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Modelcited by 45
  11. 2020Realistic Adversarial Data Augmentation for MR Image Segmentationcited by 44
  12. 2019Semi-Supervised and Task-Driven Data Augmentationcited by 40
  13. 2019Curriculum semi-supervised segmentationcited by 27
  14. 2020Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentationcited by 24
  15. 2020Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistencycited by 10
  16. 2020Learning To Pay Attention To Mistakescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 3; 2026: 1.

10 papers.

  1. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 74
  2. 2024Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentationcited by 29
  3. 2022Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentationcited by 5
  4. 2025Text-driven Multiplanar Visual Interaction for Semi-supervised Medical Image Segmentationcited by 4
  5. 2023Expectation Maximization Pseudo Labelscited by 2
  6. 2026Bidirectional Channel-selective Semantic Interaction for Semi-Supervised Medical Segmentationcited by 2
  7. 2025Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentationcited by 1
  8. 2023C3PS: Context-aware Conditional Cross Pseudo Supervision for Semi-supervised Medical Image Segmentationcited by 0
  9. 2024In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understandingcited by 0
  10. 2025CAD: Confidence-Aware Adaptive Displacement for Semi-Supervised Medical Image Segmentationcited by 0