Methods › Computer Vision › Generative Adversarial Networks › Relativistic GAN

Relativistic GAN

6 papers tagged archive 2025-07-28

Introduced by Alexia Jolicoeur-Martineau in The relativistic discriminator: a key element missing from standard GAN

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Relativistic GAN is a type of generative adversarial network. It has a relativistic discriminator which estimates the probability that the given real data is more realistic than a randomly sampled fake data. The idea is to endow GANs with the property that the probability of real data being real (D(xᵣ)) should decrease as the probability of fake data being real (D(x_f)) increases.

With a standard GAN, we can achieve this as follows. The standard GAN discriminator can be defined, in term of the non-transformed layer C(x), as D(x) = sigmoid(C(x)). A simple way to make discriminator relativistic - having the output of D depend on both real and fake data - is to sample from real/fake data pairs x̃ = (xᵣ, x_f) and define it as D(x̃) = sigmoid(C(xᵣ) − C(x_f)). The modification can be interpreted as: the discriminator estimates the probability that the given real data is more realistic than a randomly sampled fake data.

More generally a Relativistic GAN can be interpreted as having a discriminator of the form a(C(xᵣ)−C(x_f)), where a is the activation function, to be relativistic.

PaperSourceSee Code · eriklindernoren/PyTorch-GAN

Papers archive 2025-07-28

6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Generation3
Generative Adversarial Network2
Image Super-Resolution2
Super-Resolution2
Decoder1
Face Hallucination1
Image-to-Image Translation1
Translation1
Video Super-Resolution1

Usage over time archive 2025-07-28

Papers per year tagged with Relativistic GAN: 2018 to 2025, peak 2 2 0 2018: 2 papers 2018 2019: 1 paper 2019 2020: 0 papers 2020 2021: 1 paper 2021 2022: 0 papers 2022 2023: 1 paper 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (6 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Generative Adversarial Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections