# On the link between generative semi-supervised learning and generative open-set recognition

arXiv: https://arxiv.org/abs/2303.11702 · HTML: https://mlsanity.com/paper/2303.11702/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 58 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Semi-Supervised Learning with Generative Adversarial Networks](https://mlsanity.com/paper/1606.01583/) (2016)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [Good Semi-supervised Learning that Requires a Bad GAN](https://mlsanity.com/paper/1705.09783/) (2017)
- [Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2007.11330/) (2020)
- [Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling](https://mlsanity.com/paper/1612.06573/) (2016)
- [Automatic Cough Classification for Tuberculosis Screening in a Real-World Environment](https://mlsanity.com/paper/2103.13300/) (2021)
- [Triple Generative Adversarial Networks](https://mlsanity.com/paper/1912.09784/) (2019)
- [HexaGAN: Generative Adversarial Nets for Real World Classification](https://mlsanity.com/paper/1902.09913/) (2019)
- [Novelty Detection with GAN](https://mlsanity.com/paper/1802.10560/) (2018)
- [AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data](https://mlsanity.com/paper/2206.06959/) (2022)
- [Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition](https://mlsanity.com/paper/1908.03850/) (2019)
- [Semi-supervised Learning using Adversarial Training with Good and Bad Samples](https://mlsanity.com/paper/1910.08540/) (2019)

## Built on by (most cited first, 1 of 1)

- [Managing the unknown: a survey on Open Set Recognition and tangential areas](https://mlsanity.com/paper/2312.08785/) (2023)

## Abstract (arXiv)

This study investigates the relationship between semi-supervised learning (SSL, which is training off partially labelled datasets) and open-set recognition (OSR, which is classification with simultaneous novelty detection) under the context of generative adversarial networks (GANs). Although no previous study has formally linked SSL and OSR, their respective methods share striking similarities. Specifically, SSL-GANs and OSR-GANs require their generators to produce 'bad-looking' samples which are used to regularise their classifier networks. We hypothesise that the definitions of bad-looking samples in SSL and OSR represents the same concept and realises the same goal. More formally, bad-looking samples lie in the complementary space, which is the area between and around the boundaries of the labelled categories within the classifier's embedding space. By regularising a classifier with samples in the complementary space, classifiers achieve improved generalisation for SSL and also generalise the open space for OSR. To test this hypothesis, we compare a foundational SSL-GAN with the state-of-the-art OSR-GAN under the same SSL-OSR experimental conditions. Our results find that SSL-GANs achieve near identical results to OSR-GANs, proving the SSL-OSR link. Subsequently, to further this new research path, we compare several SSL-GANs various SSL-OSR setups which this first benchmark results. A combined framework of SSL-OSR certainly improves the practicality and cost-efficiency of classifier training, and so further theoretical and application studies are also discussed.