# Semi-supervised Learning using Adversarial Training with Good and Bad Samples

arXiv: https://arxiv.org/abs/1910.08540 · HTML: https://mlsanity.com/paper/1910.08540/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 2 of 2)

- [Semi-supervised Bladder Tissue Classification in Multi-Domain Endoscopic Images](https://mlsanity.com/paper/2212.11375/) (2022)
- [On the link between generative semi-supervised learning and generative open-set recognition](https://mlsanity.com/paper/2303.11702/) (2023)

## Abstract (arXiv)

In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, generates suitable image-label pairs to compensate for the lack of labeled data in SSL with improved benchmark performance. Conversely, Bad (or complementary) GAN, optimizes generation to produce complementary data-label pairs and force a classifier's decision boundary to lie between data manifolds. Although it generally outperforms Triple-GAN, Bad GAN is highly sensitive to the amount of labeled data used for training. Unifying these two approaches, we present unified-GAN (UGAN), a novel framework that enables a classifier to simultaneously learn from both good and bad samples through adversarial training. We perform extensive experiments on various datasets and demonstrate that UGAN: 1) achieves state-of-the-art performance among other deep generative models, and 2) is robust to variations in the amount of labeled data used for training.