# An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2211.11086 · HTML: https://mlsanity.com/paper/2211.11086/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 20 Nov 2022.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [What makes ImageNet good for transfer learning?](https://mlsanity.com/paper/1608.08614/) (2016)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2007.08844/) (2020)
- [AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation](https://mlsanity.com/paper/2106.04732/) (2021)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2110.10368/) (2021)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning](https://mlsanity.com/paper/2007.01293/) (2020)
- [DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.05682/) (2021)
- [CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2112.04564/) (2021)

## Built on by (most cited first, 12 of 12)

- [Exploring Vision-Language Models for Imbalanced Learning](https://mlsanity.com/paper/2304.01457/) (2023)
- [Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2310.11320/) (2023)
- [DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2307.11960/) (2023)
- [SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation](https://mlsanity.com/paper/2504.06389/) (2025)
- [S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2407.07763/) (2024)
- [Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2410.14210/) (2024)
- [Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment](https://mlsanity.com/paper/2407.05370/) (2024)
- [CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detection](https://mlsanity.com/paper/2410.04426/) (2024)
- [Leveraging Textual Anatomical Knowledge for Class-Imbalanced Semi-Supervised Multi-Organ Segmentation](https://mlsanity.com/paper/2501.13470/) (2025)
- [Boosting Semi-Supervised Medical Image Segmentation via Masked Image Consistency and Discrepancy Learning](https://mlsanity.com/paper/2503.14013/) (2025)
- [Diverse Teaching and Label Propagation for Generic Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2508.08549/) (2025)
- [Semantic Class Distribution Learning for Debiasing Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2603.05202/) (2026)

## Abstract (arXiv)

Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data. Although there are existing endeavors to tackle this challenge, their performance degenerates when facing severe imbalance since they can not reduce the class imbalance sufficiently and effectively. In this paper, we study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance by simply supplementing labeled data with pseudo-labels, according to the difference in class distribution from the most frequent class. Such a simple baseline turns out to be highly effective in reducing class imbalance. It outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and 16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127 respectively. The reduced imbalance results in faster convergence and better pseudo-label accuracy of SimiS. The simplicity of our method also makes it possible to be combined with other re-balancing techniques to improve the performance further. Moreover, our method shows great robustness to a wide range of data distributions, which holds enormous potential in practice. Code will be publicly available.