# Adversarial Transformations for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1911.06181 · HTML: https://mlsanity.com/paper/1911.06181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [TeachAugment: Data Augmentation Optimization Using Teacher Knowledge](https://mlsanity.com/paper/2202.12513/) (2022)
- [Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation](https://mlsanity.com/paper/2108.03429/) (2021)
- [Semi-Supervised Learning with Multi-Head Co-Training](https://mlsanity.com/paper/2107.04795/) (2021)
- [SemiReward: A General Reward Model for Semi-supervised Learning](https://mlsanity.com/paper/2310.03013/) (2023)
- [Adversarial and Random Transformations for Robust Domain Adaptation and Generalization](https://mlsanity.com/paper/2211.06788/) (2022)
- [Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2410.14210/) (2024)

## Abstract (arXiv)

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of class prediction for a given data against input perturbation. RAT is an extension of Virtual Adversarial Training (VAT) in such a way that RAT adversarialy transforms data along the underlying data distribution by a rich set of data transformation functions that leave class label invariant, whereas VAT simply produces adversarial additive noises. In addition, we verified that a technique of gradually increasing of perturbation region further improve the robustness. In experiments, we show that RAT significantly improves classification performance on CIFAR-10 and SVHN compared to existing regularization methods under standard semi-supervised image classification settings.