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

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Projection Cuts; projection agents; Projection Kernel; Intent Projection; projection operator; max-projection loss; subgraph projection; RBFN projection head.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 135 · with a code link: 70 · where Syntology ran a sample: 23 (19 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (23 of 135 tagged: 19 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 135, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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