mlsanityData to 7 Oct 2026

Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey

arXiv 2203.00190 ↗First posted 1 Mar 2022cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely on the abundance of labelled observations to train a prospective model. These models are composed of millions of parameters to estimate, increasing the need of more training observations. Frequently it is expensive to gather labelled observations of data, making the usage of deep learning models not ideal, as the model might over-fit data. In a semi-supervised setting, unlabelled data is used to improve the levels of accuracy and generalization of a model with small labelled datasets. Nevertheless, in many situations different unlabelled data sources might be available. This raises the risk of a significant distribution mismatch between the labelled and unlabelled datasets. Such phenomena can cause a considerable performance hit to typical semi-supervised deep learning frameworks, which often assume that both labelled and unlabelled datasets are drawn from similar distributions. Therefore, in this paper we study the latest approaches for semi-supervised deep learning for image recognition. Emphasis is made in semi-supervised deep learning models designed to deal with a distribution mismatch between the labelled and unlabelled datasets. We address open challenges with the aim to encourage the community to tackle them, and overcome the high data demand of traditional deep learning pipelines under real-world usage settings.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 54 of its 103 references that are in the map. First posted on arXiv 1 Mar 2022.

Builds on

54 of 103 references.

References · 54

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2016Concrete Problems in AI Safetycited by 1,582
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  10. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  12. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
38 more
  1. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  2. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  3. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  4. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  5. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  6. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  7. 2018A Survey on Deep Transfer Learningcited by 417
  8. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  9. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  10. 2014Learning with Pseudo-Ensemblescited by 241
  11. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 178
  12. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
  13. 2018Deep Co-Training for Semi-Supervised Image Recognitioncited by 145
  14. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  15. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  16. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  17. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 85
  18. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  19. 2019Generative Adversarial Minority Oversamplingcited by 72
  20. 2017Triple Generative Adversarial Netscited by 59
  21. 2017Deep Over-sampling Framework for Classifying Imbalanced Datacited by 58
  22. 2020A survey on Semi-, Self- and Unsupervised Learning for Image Classificationcited by 55
  23. 2017Smooth Neighbors on Teacher Graphs for Semi-supervised Learningcited by 48
  24. 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
  25. 2020Uncertainty Estimation Using a Single Deep Deterministic Neural Networkcited by 37
  26. 2019Deep Transfer Learning for Multiple Class Novelty Detectioncited by 33
  27. 2019Semi-Supervised Learning by Augmented Distribution Alignmentcited by 30
  28. 2020Class-Imbalanced Semi-Supervised Learningcited by 28
  29. 2017Data Augmentation in Emotion Classification Using Generative Adversarial Networkscited by 19
  30. 2019Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learningcited by 15
  31. 2018Rare Event Detection using Disentangled Representation Learningcited by 12
  32. 2014A Survey on Semi-Supervised Learning Techniquescited by 11
  33. 2019RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithmscited by 11
  34. 2020Correcting Data Imbalance for Semi-Supervised Covid-19 Detection Using X-ray Chest Imagescited by 9
  35. 2017Pediatric Bone Age Assessment Using Deep Convolutional Neural Networkscited by 4
  36. 2018SaaS: Speed as a Supervisor for Semi-supervised Learningcited by 4
  37. 2019Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approachcited by 4
  38. 2019Semi-supervised Learning of Fetal Anatomy from Ultrasoundcited by 4

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 5.

8 papers.

  1. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  2. 2024ShadowMaskFormer: Mask Augmented Patch Embeddings for Shadow Removalcited by 7
  3. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  4. 2024Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methodscited by 2
  5. 2023A Novel Dataset for Financial Education Text Simplification in Spanishcited by 1
  6. 2024Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Tool Segmentation in Robot-Assisted Cardiovascular Catheterizationcited by 1
  7. 2022Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Imagescited by 0
  8. 2024Theory-inspired Label Shift Adaptation via Aligned Distribution Mixturecited by 0