mlsanityData to 7 Oct 2026

Curriculum semi-supervised segmentation

arXiv 1904.05236 ↗First posted 10 Apr 2019cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region. These regressions are used to effectively regularize the segmentation network, constraining softmax predictions of the unlabeled images to match the inferred label distributions. Our framework is based on inequality constraints that tolerate uncertainties with inferred knowledge, e.g., regressed region size, and can be employed for a large variety of region attributes. We evaluated our proposed strategy for left ventricle segmentation in magnetic resonance images (MRI), and compared it to standard proposal-based semi-supervision strategies. Our strategy leverages unlabeled data in more efficiently, and achieves very competitive results, approaching the performance of full-supervision.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 7; 2023: 3; 2024: 1; 2025: 1.

27 papers.

Sort:

  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  2. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  3. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 99
  4. 2021Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentationcited by 61
  5. 2021Source-Free Domain Adaptation for Image Segmentationcited by 45
  6. 2021Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentationcited by 33
  7. 2022Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillationcited by 26
  8. 2021Medical Image Segmentation with Limited Supervision: A Review of Deep Network Modelscited by 21
  9. 2022Constrained unsupervised anomaly segmentationcited by 19
  10. 2021Weakly supervised segmentation with cross-modality equivariant constraintscited by 18
  11. 2023Towards Open-World Segmentation of Partscited by 15
  12. 2022Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentationcited by 10
15 more
  1. 2023ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrastcited by 9
  2. 2022Negative Evidence Matters in Interpretable Histology Image Classificationcited by 8
  3. 2021Segmentation with mixed supervision: Confidence maximization helps knowledge distillationcited by 6
  4. 2021Looking at the whole picture: constrained unsupervised anomaly segmentationcited by 4
  5. 2021Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detectioncited by 3
  6. 2021POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboringcited by 3
  7. 2021Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Imagescited by 3
  8. 2022Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentationcited by 3
  9. 2022On the pitfalls of entropy-based uncertainty for multi-class semi-supervised segmentationcited by 2
  10. 2024Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classificationcited by 2
  11. 2021Transductive image segmentation: Self-training and effect of uncertainty estimationcited by 1
  12. 2021MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labelscited by 1
  13. 2023A New Perspective to Boost Vision Transformer for Medical Image Classificationcited by 1
  14. 2021Bladder segmentation based on deep learning approaches: current limitations and lessonscited by 0
  15. 2025Dual-Scale Volume Priors with Wasserstein-Based Consistency for Semi-Supervised Medical Image Segmentationcited by 0