mlsanityData to 7 Oct 2026

Discriminator Rejection Sampling

arXiv 1810.06758 ↗First posted 16 Oct 2018stat.ML cs.LGcited by 48

Not on the map. Why?

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.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 12; 2023: 7; 2024: 7; 2025: 4; 2026: 4.

48 papers.

Sort:

By area:

  1. 2022High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditionscited by 129
  2. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Modelscited by 98
  3. 2022Generating High Fidelity Data from Low-density Regions using Diffusion Modelscited by 78
  4. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  5. 2023RadEdit: stress-testing biomedical vision models via diffusion image editingcited by 28
  6. 2021Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognitioncited by 24
  7. 2022Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Valuescited by 21
  8. 2022FairStyle: Debiasing StyleGAN2 with Style Channel Manipulationscited by 20
  9. 2021Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networkscited by 13
  10. 2024Diffusion Rejection Samplingcited by 11
  11. 2021Partition-Guided GANscited by 9
  12. 2021BIGRoC: Boosting Image Generation via a Robust Classifiercited by 9
36 more
  1. 2023Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flowscited by 9
  2. 2025Preference Optimization by Estimating the Ratio of the Data Distributioncited by 9
  3. 2021Model Extraction and Defenses on Generative Adversarial Networkscited by 8
  4. 2022Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoderscited by 8
  5. 2024Assessing Sample Quality via the Latent Space of Generative Modelscited by 8
  6. 2024Efficient Diversity-based Experience Replay for Deep Reinforcement Learningcited by 7
  7. 2021Latent reweighting, an almost free improvement for GANscited by 6
  8. 2023Towards Mode Balancing of Generative Models via Diversity Weightscited by 6
  9. 2023Coupled Variational Autoencodercited by 6
  10. 2023Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidancecited by 6
  11. 2021Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variablecited by 5
  12. 2022Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Samplingcited by 5
  13. 2023Discriminator Guidance for Autoregressive Diffusion Modelscited by 5
  14. 2023Optimal Budgeted Rejection Sampling for Generative Modelscited by 5
  15. 2021Mitigating Statistical Bias within Differentially Private Synthetic Datacited by 4
  16. 2022Reducing Training Sample Memorization in GANs by Training with Memorization Rejectioncited by 4
  17. 2024Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networkscited by 4
  18. 2021Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Studycited by 3
  19. 2022Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planningcited by 3
  20. 2022Unveiling the Latent Space Geometry of Push-Forward Generative Modelscited by 3
  21. 2024Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Densitycited by 3
  22. 2024Diverse Rare Sample Generation with Pretrained GANscited by 3
  23. 2021Reparameterized Sampling for Generative Adversarial Networkscited by 2
  24. 2021Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunitiescited by 2
  25. 2021Single volume lung biomechanics from chest computed tomography using a mode preserving generative adversarial networkcited by 2
  26. 2024CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systemscited by 2
  27. 2025Improving Discriminator Guidance in Diffusion Modelscited by 2
  28. 2022Mining Multi-Label Samples from Single Positive Labelscited by 1
  29. 2025Studying Classifier(-Free) Guidance From a Classifier-Centric Perspectivecited by 1
  30. 2025Inference-time Stochastic Refinement of GRU-Normalizing Flow for Real-time Video Motion Transfercited by 1
  31. 2021Variational Rejection Particle Filteringcited by 0
  32. 2021Deep Probabilistic Graphical Modelingcited by 0
  33. 2026Learning To Sample From Diffusion Models Via Inverse Reinforcement Learningcited by 0
  34. 2026Improving Generative Adversarial Networks with Self-Distillationcited by 0
  35. 2026Implicit Variational Rejection Samplingcited by 0
  36. 2026DS@GT ARC at ImageCLEFmed GANs 2026: Geometric Filtering for Privacy-Preserving CT Slice Generationcited by 0