# Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators

arXiv: https://arxiv.org/abs/1807.11346 · HTML: https://mlsanity.com/paper/1807.11346/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2018.

## Built on by (most cited first, 15 of 15)

- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [HumanGAN: A Generative Model of Humans Images](https://mlsanity.com/paper/2103.06902/) (2021)
- [VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting](https://mlsanity.com/paper/2201.04873/) (2022)
- [Synthetic data, real errors: how (not) to publish and use synthetic data](https://mlsanity.com/paper/2305.09235/) (2023)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [G3FA: Geometry-guided GAN for Face Animation](https://mlsanity.com/paper/2408.13049/) (2024)
- [Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing](https://mlsanity.com/paper/2103.11912/) (2021)
- [FlexiDrop: Theoretical Insights and Practical Advances in Random Dropout Method on GNNs](https://mlsanity.com/paper/2405.20012/) (2024)
- [HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization](https://mlsanity.com/paper/2503.19074/) (2025)
- [Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation](https://mlsanity.com/paper/2503.24258/) (2025)
- [Prb-GAN: A Probabilistic Framework for GAN Modelling](https://mlsanity.com/paper/2107.05241/) (2021)
- [Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers](https://mlsanity.com/paper/2112.15111/) (2021)
- [Social Media Bot Detection using Dropout-GAN](https://mlsanity.com/paper/2311.05079/) (2023)
- [Improving Temporal Consistency and Fidelity at Inference-time in Perceptual Video Restoration by Zero-shot Image-based Diffusion Models](https://mlsanity.com/paper/2510.25420/) (2025)
- [Synthetic Data: AI's New Weapon Against Android Malware](https://mlsanity.com/paper/2511.19649/) (2025)

## Abstract (arXiv)

We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator, but, instead, to satisfy a dynamic ensemble of discriminators. We show that this leads to a more generalized generator, promoting variety in the generated samples and avoiding the common mode collapse problem commonly experienced with generative adversarial networks (GANs). We further provide evidence that the proposed framework, named Dropout-GAN, promotes sample diversity both within and across epochs, eliminating mode collapse and stabilizing training.