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

arXiv: https://arxiv.org/abs/1911.09785 · HTML: https://mlsanity.com/paper/1911.09785/

## Key facts

- Cited by 349 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 30 of 349)

- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples](https://mlsanity.com/paper/2104.13963/) (2021)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [Describe Anything: Detailed Localized Image and Video Captioning](https://mlsanity.com/paper/2504.16072/) (2025)
- [PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training](https://mlsanity.com/paper/2105.08128/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2405.05258/) (2024)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection](https://mlsanity.com/paper/2207.02541/) (2022)
- [SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training](https://mlsanity.com/paper/2106.01432/) (2021)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (2021)
- [OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers](https://mlsanity.com/paper/2105.14148/) (2021)
- [SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies](https://mlsanity.com/paper/2106.09678/) (2021)
- [Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation](https://mlsanity.com/paper/2112.09645/) (2021)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)

## 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.