Methods › General › Discriminators › Projection Discriminator

Projection Discriminator

135 papers tagged archive 2025-07-28

Introduced by Takeru Miyato et al. in cGANs with Projection Discriminator

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

A Projection Discriminator is a type of discriminator for generative adversarial networks. It is motivated by a probabilistic model in which the distribution of the conditional variable y given x is discrete or uni-modal continuous distributions.

If we look at the original solution for the loss function ℒ_D in the vanilla GANs, we can decompose it into the sum of two log-likelihood ratios:

f^*(𝐱, 𝐲) = log(q(𝐱|𝐲)q(𝐲))/(p(𝐱|𝐲)p(𝐲)) = log(q(𝐲|𝐱))/(p(𝐲|𝐱)) + log(q(𝐱))/(p(𝐱)) = r(𝐲|𝐱) + r(𝐱)

We can model the log likelihood ratio r(𝐲|𝐱) and r(𝐱) by some parametric functions f₁ and f₂ respectively. If we make a standing assumption that p(y|x) and q(y|x) are simple distributions like those that are Gaussian or discrete log linear on the feature space, then the parametrization of the following form becomes natural:

f(𝐱, 𝐲; θ) = f₁(𝐱, 𝐲; θ) + f₂(𝐱; θ) = 𝐲ᵀVϕ(𝐱; θ_ϕ) + ψ(ϕ(𝐱; θ_ϕ); θ_ψ)

where V is the embedding matrix of y, ϕ(·, θ_ϕ) is a vector output function of x, and ψ(·, θ_ψ) is a scalar function of the same ϕ(𝐱; θ_ϕ) that appears in f₁. The learned parameters θ={V, θ_ϕ, θ_ψ} are trained to optimize the adversarial loss. This model of the discriminator is the projection.

PaperSourceSee Code · pfnet-research/sngan_projection

Papers archive 2025-07-28

30 shown of 135, 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

20 shown of 141 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 Generation39
Conditional Image Generation16
Generative Adversarial Network12
reinforcement-learning9
Multi-agent Reinforcement Learning7
Reinforcement Learning7
Super-Resolution7
Data Augmentation6
Reinforcement Learning (RL)6
Decision Making5
Unconditional Image Generation5
Vocal Bursts Intensity Prediction5
Attribute4
Clustering4
Denoising4
Diversity4
Image-to-Image Translation4
Object4
Transfer Learning4
Translation4

Usage over time archive 2025-07-28

Papers per year tagged with Projection Discriminator: 2018 to 2024, peak 38 38 0 2018: 4 papers 2018 2019: 9 papers 2019 2020: 29 papers 2020 2021: 20 papers 2021 2022: 33 papers 2022 2023: 38 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (135 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

Discriminators

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