Data to 7 Oct 2026

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

arXiv 1911.09785 ↗First posted 21 Nov 2019cs.LG cs.CV stat.MLcited by 349

Not on the map. Why?

Abstract (arXiv)

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5× and 16× less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4,000 examples) and a median accuracy of 84.92% with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch.

Key facts. Cited by 349 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 73; 2022: 90; 2023: 75; 2024: 63; 2025: 30; 2026: 18.

349 papers.

Sort:

By area:

2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
2021Open-World Semi-Supervised Learningcited by 165
2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92

38 more

2025Describe Anything: Detailed Localized Image and Video Captioningcited by 84
2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
2022Debiased Self-Training for Semi-Supervised Learningcited by 62
2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
2022Learning to Detect Mobile Objects from LiDAR Scans Without Labelscited by 44
2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
2021Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentationcited by 43
2023Active Teacher for Semi-Supervised Object Detectioncited by 43
2023Backdoor Defense via Adaptively Splitting Poisoned Datasetcited by 43
2021SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policiescited by 42
2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
2021AutoDropout: Learning Dropout Patterns to Regularize Deep Networkscited by 35
2021SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learningcited by 35
2022ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptationcited by 34
2021Reference-guided Pseudo-Label Generation for Medical Semantic Segmentationcited by 33
2021Pseudo-labeling for Scalable 3D Object Detectioncited by 32
2021MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworkscited by 32
2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
2022ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classificationcited by 30
2022Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentationcited by 30
2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
2021Direct Differentiable Augmentation Searchcited by 28
2021Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Trainingcited by 28
2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
2021Unsupervised Selective Labeling for More Effective Semi-Supervised Learningcited by 27
2021Multimodal Knowledge Expansioncited by 26
2021Semi-supervised Contrastive Learning with Similarity Co-calibrationcited by 26
2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26

50 most cited of 349 All 349 (JSON)