# Discriminator Rejection Sampling

arXiv: https://arxiv.org/abs/1810.06758 · HTML: https://mlsanity.com/paper/1810.06758/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2018.

## Built on by (most cited first, 30 of 49)

- [High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions](https://mlsanity.com/paper/2206.14180/) (2022)
- [Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models](https://mlsanity.com/paper/2211.17091/) (2022)
- [Generating High Fidelity Data from Low-density Regions using Diffusion Models](https://mlsanity.com/paper/2203.17260/) (2022)
- [GATSBI: Generative Adversarial Training for Simulation-Based Inference](https://mlsanity.com/paper/2203.06481/) (2022)
- [RadEdit: stress-testing biomedical vision models via diffusion image editing](https://mlsanity.com/paper/2312.12865/) (2023)
- [Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition](https://mlsanity.com/paper/2110.11479/) (2021)
- [Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values](https://mlsanity.com/paper/2203.01993/) (2022)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [Diffusion Rejection Sampling](https://mlsanity.com/paper/2405.17880/) (2024)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [BIGRoC: Boosting Image Generation via a Robust Classifier](https://mlsanity.com/paper/2108.03702/) (2021)
- [Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows](https://mlsanity.com/paper/2305.18910/) (2023)
- [Preference Optimization by Estimating the Ratio of the Data Distribution](https://mlsanity.com/paper/2505.19601/) (2025)
- [Model Extraction and Defenses on Generative Adversarial Networks](https://mlsanity.com/paper/2101.02069/) (2021)
- [Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders](https://mlsanity.com/paper/2208.10570/) (2022)
- [Assessing Sample Quality via the Latent Space of Generative Models](https://mlsanity.com/paper/2407.15171/) (2024)
- [Efficient Diversity-based Experience Replay for Deep Reinforcement Learning](https://mlsanity.com/paper/2410.20487/) (2024)
- [Latent reweighting, an almost free improvement for GANs](https://mlsanity.com/paper/2110.09803/) (2021)
- [Towards Mode Balancing of Generative Models via Diversity Weights](https://mlsanity.com/paper/2304.11961/) (2023)
- [Coupled Variational Autoencoder](https://mlsanity.com/paper/2306.02565/) (2023)
- [Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance](https://mlsanity.com/paper/2307.16463/) (2023)
- [Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable](https://mlsanity.com/paper/2103.11166/) (2021)
- [Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling](https://mlsanity.com/paper/2212.02090/) (2022)
- [Discriminator Guidance for Autoregressive Diffusion Models](https://mlsanity.com/paper/2310.15817/) (2023)
- [Optimal Budgeted Rejection Sampling for Generative Models](https://mlsanity.com/paper/2311.00460/) (2023)
- [Mitigating Statistical Bias within Differentially Private Synthetic Data](https://mlsanity.com/paper/2108.10934/) (2021)
- [Reducing Training Sample Memorization in GANs by Training with Memorization Rejection](https://mlsanity.com/paper/2210.12231/) (2022)
- [Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks](https://mlsanity.com/paper/2404.13634/) (2024)
- [Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study](https://mlsanity.com/paper/2107.12202/) (2021)

## Abstract (arXiv)

We propose a rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution. We show that under quite strict assumptions, this will allow us to recover the data distribution exactly. We then examine where those strict assumptions break down and design a practical algorithm - called Discriminator Rejection Sampling (DRS) - that can be used on real data-sets. Finally, we demonstrate the efficacy of DRS on a mixture of Gaussians and on the SAGAN model, state-of-the-art in the image generation task at the time of developing this work. On ImageNet, we train an improved baseline that increases the Inception Score from 52.52 to 62.36 and reduces the Frechet Inception Distance from 18.65 to 14.79. We then use DRS to further improve on this baseline, improving the Inception Score to 76.08 and the FID to 13.75.