# The relativistic discriminator: a key element missing from standard GAN

arXiv: https://arxiv.org/abs/1807.00734 · HTML: https://mlsanity.com/paper/1807.00734/

## Key facts

- Cited by 238 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 30 of 238)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution](https://mlsanity.com/paper/2203.09195/) (2022)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2506.09350/) (2025)
- [Align Your Flow: Scaling Continuous-Time Flow Map Distillation](https://mlsanity.com/paper/2506.14603/) (2025)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation](https://mlsanity.com/paper/2102.01187/) (2021)
- [Free-viewpoint Indoor Neural Relighting from Multi-view Stereo](https://mlsanity.com/paper/2106.13299/) (2021)
- [SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training](https://mlsanity.com/paper/2506.05301/) (2025)
- [Training GANs with Stronger Augmentations via Contrastive Discriminator](https://mlsanity.com/paper/2103.09742/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection](https://mlsanity.com/paper/2305.06321/) (2023)
- [Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation](https://mlsanity.com/paper/2110.10546/) (2021)
- [Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning](https://mlsanity.com/paper/2309.11359/) (2023)
- [Best-Buddy GANs for Highly Detailed Image Super-Resolution](https://mlsanity.com/paper/2103.15295/) (2021)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training](https://mlsanity.com/paper/2204.02844/) (2022)
- [DeFLOCNet: Deep Image Editing via Flexible Low-level Controls](https://mlsanity.com/paper/2103.12723/) (2021)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)

## Abstract (arXiv)

In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also simultaneously decrease the probability that real data is real because 1) this would account for a priori knowledge that half of the data in the mini-batch is fake, 2) this would be observed with divergence minimization, and 3) in optimal settings, SGAN would be equivalent to integral probability metric (IPM) GANs. We show that this property can be induced by using a relativistic discriminator which estimate the probability that the given real data is more realistic than a randomly sampled fake data. We also present a variant in which the discriminator estimate the probability that the given real data is more realistic than fake data, on average. We generalize both approaches to non-standard GAN loss functions and we refer to them respectively as Relativistic GANs (RGANs) and Relativistic average GANs (RaGANs). We show that IPM-based GANs are a subset of RGANs which use the identity function. Empirically, we observe that 1) RGANs and RaGANs are significantly more stable and generate higher quality data samples than their non-relativistic counterparts, 2) Standard RaGAN with gradient penalty generate data of better quality than WGAN-GP while only requiring a single discriminator update per generator update (reducing the time taken for reaching the state-of-the-art by 400%), and 3) RaGANs are able to generate plausible high resolutions images (256x256) from a very small sample (N=2011), while GAN and LSGAN cannot; these images are of significantly better quality than the ones generated by WGAN-GP and SGAN with spectral normalization.