Methods › General › Discriminators › Projection Discriminator
Projection Discriminator
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.
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.
-
ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks 6 Nov 2024 · 0 repositories · arXiv:2411.03999
-
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization 27 Oct 2024 · 1 repository · arXiv:2410.20573
-
On quantifying and improving realism of images generated with diffusion 26 Sep 2023 · 0 repositories · arXiv:2309.14756
-
Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows 21 Sep 2023 · 0 repositories
-
A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory 27 Jul 2023 · 2 repositories · arXiv:2307.14732
-
Pyrus Base: An Open Source Python Framework for the RoboCup 2D Soccer Simulation 22 Jul 2023 · 1 repository · arXiv:2307.16875
-
Diffusion Models Beat GANs on Image Classification 17 Jul 2023 · 1 repository · arXiv:2307.08702
-
Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs 28 Jun 2023 · 0 repositories · arXiv:2306.15903
-
Rosetta Neurons: Mining the Common Units in a Model Zoo 15 Jun 2023 · 0 repositories · arXiv:2306.09346
-
Toward more accurate and generalizable brain deformation estimators for traumatic brain injury detection with unsupervised domain adaptation 8 Jun 2023 · 0 repositories · arXiv:2306.05255
-
FOOCTTS: Generating Arabic Speech with Acoustic Environment for Football Commentator 7 Jun 2023 · 0 repositories · arXiv:2306.07936
-
Action valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning 29 May 2023 · 0 repositories · arXiv:2305.17886
-
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL? 27 May 2023 · 1 repository · arXiv:2305.17352Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations 22 May 2023 · 0 repositories · arXiv:2305.13030
-
An Empirical Study on Google Research Football Multi-agent Scenarios 16 May 2023 · 1 repository · arXiv:2305.09458
-
The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation 5 May 2023 · 1 repository · arXiv:2305.03369
-
SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes 11 Apr 2023 · 1 repository · arXiv:2304.05170
-
VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views 10 Apr 2023 · 1 repository · arXiv:2304.04617
-
Towards Active Learning for Action Spotting in Association Football Videos 9 Apr 2023 · 0 repositories · arXiv:2304.04220
-
Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football 25 Mar 2023 · 0 repositories · arXiv:2303.15471
-
Deep Generative Multi-Agent Imitation Model as a Computational Benchmark for Evaluating Human Performance in Complex Interactive Tasks: A Case Study in Football 23 Mar 2023 · 0 repositories · arXiv:2303.13323
-
High Fidelity Image Synthesis With Deep VAEs In Latent Space 23 Mar 2023 · 2 repositories · arXiv:2303.13714Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
-
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images 13 Mar 2023 · 0 repositories · arXiv:2303.07274
-
NFL Career Success as Predicted by NFL Scouting Combine 10 Mar 2023 · 1 repository · arXiv:2303.05774
-
Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning 7 Mar 2023 · 1 repository · arXiv:2303.08046
-
Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs 3 Mar 2023 · 0 repositories · arXiv:2303.01991
-
Identification of pattern mining algorithm for rugby league players positional groups separation based on movement patterns 25 Feb 2023 · 0 repositories · arXiv:2302.14058
-
Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis 18 Feb 2023 · 1 repository · arXiv:2302.09276
-
TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play 15 Feb 2023 · 1 repository · arXiv:2302.07515
-
Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations 13 Feb 2023 · 0 repositories · arXiv:2302.06569
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.
Usage over time archive 2025-07-28
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
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