# On Positive-Unlabeled Classification in GAN

arXiv: https://arxiv.org/abs/2002.01136 · HTML: https://mlsanity.com/paper/2002.01136/

## Key facts

- Cited by 14 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 4 Feb 2020.

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

- [HairCLIP: Design Your Hair by Text and Reference Image](https://mlsanity.com/paper/2112.05142/) (2021)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [Training-free Composite Scene Generation for Layout-to-Image Synthesis](https://mlsanity.com/paper/2407.13609/) (2024)
- [Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends](https://mlsanity.com/paper/2310.04078/) (2023)
- [Active Generation for Image Classification](https://mlsanity.com/paper/2403.06517/) (2024)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Font Generation with Missing Impression Labels](https://mlsanity.com/paper/2203.10348/) (2022)
- [Boosting Diffusion Models with an Adaptive Momentum Sampler](https://mlsanity.com/paper/2308.11941/) (2023)
- [Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning](https://mlsanity.com/paper/2302.06271/) (2023)
- [Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions](https://mlsanity.com/paper/2411.10364/) (2024)
- [Learning from Positive and Unlabeled Data with Augmented Classes](https://mlsanity.com/paper/2207.13274/) (2022)
- [Learning from Label Proportions with Dual-proportion Constraints](https://mlsanity.com/paper/2603.21153/) (2026)
- [Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data](https://mlsanity.com/paper/2606.30192/) (2026)

## Abstract (arXiv)

This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification criterion was kept fixed all through the learning process of the discriminator without considering the gradually improved quality of generated data, even if they could be more realistic than real data at times. In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality. The discriminator is thus a classifier for this positive and unlabeled classification problem, and we derive a new Positive-Unlabeled GAN (PUGAN). We theoretically discuss the global optimality the proposed model will achieve and the equivalent optimization goal. Empirically, we find that PUGAN can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.