mlsanityData to 14 Oct 2026

Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning

arXiv 1606.04586 ↗First posted 14 Jun 2016cs.CVcited by 441

Not on the map. Why?

Abstract (arXiv)

Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher accuracy when there is a limited set of labeled data available. In this paper, we consider the problem of semi-supervised learning with convolutional neural networks. Techniques such as randomized data augmentation, dropout and random max-pooling provide better generalization and stability for classifiers that are trained using gradient descent. Multiple passes of an individual sample through the network might lead to different predictions due to the non-deterministic behavior of these techniques. We propose an unsupervised loss function that takes advantage of the stochastic nature of these methods and minimizes the difference between the predictions of multiple passes of a training sample through the network. We evaluate the proposed method on several benchmark datasets.

Key facts. Cited by 441 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 111; 2022: 119; 2023: 93; 2024: 75; 2025: 33; 2026: 10.

441 papers.

Sort:

By area:

  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  2. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 382
  3. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  4. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  5. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  6. 2021A Survey on Deep Semi-supervised Learningcited by 251
  7. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  8. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  9. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  10. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  11. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  12. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
38 more
  1. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  2. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  3. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 148
  4. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  5. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  6. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  7. 2021Cycle Self-Training for Domain Adaptationcited by 120
  8. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 119
  9. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  10. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  11. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 113
  12. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  13. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  14. 2022SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learningcited by 97
  15. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  16. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  17. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  18. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  19. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 76
  20. 2022Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectorscited by 69
  21. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  22. 2022Prompt Consistency for Zero-Shot Task Generalizationcited by 67
  23. 2021Local Augmentation for Graph Neural Networkscited by 53
  24. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  25. 2021Consistency Regularization for Variational Auto-Encoderscited by 51
  26. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  27. 2021Online Adversarial Purification based on Self-Supervisioncited by 46
  28. 2022Label Matching Semi-Supervised Object Detectioncited by 44
  29. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 44
  30. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  31. 2021SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Drivingcited by 43
  32. 2021Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentationcited by 43
  33. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  34. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
  35. 2021Self-supervised driven consistency training for annotation efficient histopathology image analysiscited by 39
  36. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  37. 2021Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularizationcited by 36
  38. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36

50 most cited of 441 All 441 (JSON)