# RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms

arXiv: https://arxiv.org/abs/1912.08766 · HTML: https://mlsanity.com/paper/1912.08766/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data](https://mlsanity.com/paper/2107.08943/) (2021)
- [Robust Semi-supervised Learning by Wisely Leveraging Open-set Data](https://mlsanity.com/paper/2405.06979/) (2024)
- [MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels](https://mlsanity.com/paper/2103.10368/) (2021)
- [RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data](https://mlsanity.com/paper/2302.14483/) (2023)
- [Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey](https://mlsanity.com/paper/2203.00190/) (2022)
- [Semi-Supervised Learning of Classifiers from a Statistical Perspective: A Brief Review](https://mlsanity.com/paper/2104.04046/) (2021)
- [AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data](https://mlsanity.com/paper/2206.06959/) (2022)
- [Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities](https://mlsanity.com/paper/2109.00889/) (2021)
- [ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation](https://mlsanity.com/paper/2102.06328/) (2021)
- [RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss](https://mlsanity.com/paper/2110.04430/) (2021)
- [Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data](https://mlsanity.com/paper/2112.02825/) (2021)

## Abstract (arXiv)

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior SSL algorithms suffer from. In particular, poor performance when unlabeled and labeled data distributions differ. To address these observations, we develop RealMix, which achieves state-of-the-art results on standard benchmark datasets across different labeled and unlabeled set sizes while overcoming the aforementioned challenges. Notably, RealMix achieves an error rate of 9.79% on CIFAR10 with 250 labels and is the only SSL method tested able to surpass baseline performance when there is significant mismatch in the labeled and unlabeled data distributions. RealMix demonstrates how SSL can be used in real world situations with limited access to both data and compute and guides further research in SSL with practical applicability in mind.