mlsanityData to 14 Oct 2026

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data

arXiv 2206.06959 ↗First posted 14 Jun 2022cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this work, we show that state-of-the-art SSL algorithms suffer a degradation in performance in the presence of unlabeled auxiliary data that does not necessarily possess the same class distribution as the labeled set. We term this problem as Auxiliary-SSL and propose AuxMix, an algorithm that leverages self-supervised learning tasks to learn generic features in order to mask auxiliary data that are not semantically similar to the labeled set. We also propose to regularize learning by maximizing the predicted entropy for dissimilar auxiliary samples. We show an improvement of 5% over existing baselines on a ResNet-50 model when trained on CIFAR10 dataset with 4k labeled samples and all unlabeled data is drawn from the Tiny-ImageNet dataset. We report competitive results on several datasets and conduct ablation studies.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

31 of 48 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2016Wide Residual Networkscited by 3,070
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  9. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  11. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  12. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
19 more
  1. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  2. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  3. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  5. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
  6. 2020Meta Pseudo Labelscited by 374
  7. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  8. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  9. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  10. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  11. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 251
  12. 2014Learning with Pseudo-Ensemblescited by 241
  13. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  14. 2021SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learningcited by 35
  15. 2021SimROD: A Simple Adaptation Method for Robust Object Detectioncited by 27
  16. 2019Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activationscited by 13
  17. 2019RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithmscited by 11
  18. 2021Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examplescited by 5
  19. 2021Revisiting Knowledge Distillation for Object Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 1.

4 papers.

  1. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  2. 2023On the link between generative semi-supervised learning and generative open-set recognitioncited by 1
  3. 2023Exploring the Boundaries of Semi-Supervised Facial Expression Recognition using In-Distribution, Out-of-Distribution, and Unconstrained Datacited by 1
  4. 2025Severity Classification of Chronic Obstructive Pulmonary Disease in Intensive Care Units: A Semi-Supervised Approach Using MIMIC-III Datasetcited by 0