# Semi-supervised semantic segmentation needs strong, varied perturbations

arXiv: https://arxiv.org/abs/1906.01916 · HTML: https://mlsanity.com/paper/1906.01916/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training](https://mlsanity.com/paper/2105.08128/) (2021)
- [Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation](https://mlsanity.com/paper/2112.00735/) (2021)
- [All you need are a few pixels: semantic segmentation with PixelPick](https://mlsanity.com/paper/2104.06394/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Robust Mutual Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.00609/) (2021)
- [Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations](https://mlsanity.com/paper/2210.14670/) (2022)
- [The Effects of Mixed Sample Data Augmentation are Class Dependent](https://mlsanity.com/paper/2307.09136/) (2023)
- [VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2503.10685/) (2025)
- [What is the Added Value of UDA in the VFM Era?](https://mlsanity.com/paper/2504.18190/) (2025)
- [Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification](https://mlsanity.com/paper/2212.00214/) (2022)
- [Embracing Annotation Efficient Learning (AEL) for Digital Pathology and Natural Images](https://mlsanity.com/paper/2212.00470/) (2022)
- [Exploring Probabilistic Models for Semi-supervised Learning](https://mlsanity.com/paper/2404.04199/) (2024)
- [Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2411.05307/) (2024)
- [Adaptively Augmented Consistency Learning: A Semi-supervised Segmentation Framework for Remote Sensing](https://mlsanity.com/paper/2411.09344/) (2024)

## Abstract (arXiv)

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists of uniform class clusters of samples separated by low density regions - as important to its success. We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success. We then identify choice of augmentation as key to obtaining reliable performance without such low-density regions. We find that adapted variants of the recently proposed CutOut and CutMix augmentation techniques yield state-of-the-art semi-supervised semantic segmentation results in standard datasets. Furthermore, given its challenging nature we propose that semantic segmentation acts as an effective acid test for evaluating semi-supervised regularizers. Implementation at: https://github.com/Britefury/cutmix-semisup-seg.