mlsanityData to 14 Oct 2026

RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

arXiv 2302.14483 ↗First posted 28 Feb 2023cs.LG cs.CV stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data. However, PAWS is often less effective when using real-world unlabeled data that is uncurated, e.g., contains out-of-class data. We propose RoPAWS, a robust extension of PAWS that can work with real-world unlabeled data. We first reinterpret PAWS as a generative classifier that models densities using kernel density estimation. From this probabilistic perspective, we calibrate its prediction based on the densities of labeled and unlabeled data, which leads to a simple closed-form solution from the Bayes' rule. We demonstrate that RoPAWS significantly improves PAWS for uncurated Semi-iNat by +5.3% and curated ImageNet by +0.4%.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 67 of its 93 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

67 of 93 references.

References · 67

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2016Wide Residual Networkscited by 3,070
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
38 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  2. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  5. 2019When Does Label Smoothing Help?cited by 988
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  8. 2017Large Batch Training of Convolutional Networkscited by 535
  9. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  10. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  11. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  13. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  14. 2020Meta Pseudo Labelscited by 374
  15. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  16. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  17. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  18. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  19. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  20. 2022Generalized Category Discoverycited by 211
  21. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
  22. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  23. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  24. 2018Reducing Network Agnostophobiacited by 165
  25. 2021Open-World Semi-Supervised Learningcited by 165
  26. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  27. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  28. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  29. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  30. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 82
  31. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  32. 2021RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learningcited by 74
  33. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  34. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  35. 2020FeatMatch: Feature-Based Augmentation for Semi-Supervised Learningcited by 57
  36. 2020Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learningcited by 53
  37. 2022Semi-supervised Vision Transformers at Scalecited by 49
  38. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 4; 2025: 3.

10 papers.

  1. 2023S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captionscited by 30
  2. 2024Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognitioncited by 10
  3. 2024Improving Concept Alignment in Vision-Language Concept Bottleneck Modelscited by 4
  4. 2024ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detectioncited by 3
  5. 2025Open Ad-hoc Categorization with Contextualized Feature Learningcited by 3
  6. 2023A Mixture of Exemplars Approach for Efficient Out-of-Distribution Detection with Foundation Modelscited by 2
  7. 2024ComFe: An Interpretable Head for Vision Transformerscited by 2
  8. 2025Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learningcited by 2
  9. 2023SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentationcited by 1
  10. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0