Methods › General › Self-Supervised Learning › BiGAN

Bidirectional GAN

BiGAN

15 papers tagged archive 2025-07-28

Introduced by Jeff Donahue et al. in Adversarial Feature Learning

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

A BiGAN, or Bidirectional GAN, is a type of generative adversarial network where the generator not only maps latent samples to generated data, but also has an inverse mapping from data to the latent representation. The motivation is to make a type of GAN that can learn rich representations for us in applications like unsupervised learning.

In addition to the generator G from the standard GAN framework, BiGAN includes an encoder E which maps data 𝐱 to latent representations 𝐳. The BiGAN discriminator D discriminates not only in data space (𝐱 versus G(𝐳)), but jointly in data and latent space (tuples (𝐱, E(𝐱)) versus (G(z), z)), where the latent component is either an encoder output E(𝐱) or a generator input 𝐳.

PaperSourceSee Code · jeffdonahue/bigan

Papers archive 2025-07-28

15 shown of 15, 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 28 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
Decoder2
General Classification2
Image Generation2
Adversarial Attack1
Anomaly Detection1
Atari Games1
Conditional Image Generation1
Data Augmentation1
Deep Reinforcement Learning1
Density Estimation1
Dimensionality Reduction1
Diversity1
Face Generation1
Generative Adversarial Network1
Image Classification1
Image Retrieval1
Image-to-Image Translation1
MuJoCo1
Outlier Detection1
Reinforcement Learning1

Usage over time archive 2025-07-28

Papers per year tagged with BiGAN: 2016 to 2025, peak 3 3 0 2016: 2 papers 2016 2017: 1 paper 2017 2018: 3 papers 2018 2019: 1 paper 2019 2020: 3 papers 2020 2021: 2 papers 2021 2022: 2 papers 2022 2023: 0 papers 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (15 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

Self-Supervised LearningGenerative Adversarial NetworksGenerative Models

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