Methods › General › Regularization › GAN Feature Matching

GAN Feature Matching

16 papers tagged archive 2025-07-28

Introduced by Tim Salimans et al. in Improved Techniques for Training GANs

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

Feature Matching is a regularizing objective for a generator in generative adversarial networks that prevents it from overtraining on the current discriminator. Instead of directly maximizing the output of the discriminator, the new objective requires the generator to generate data that matches the statistics of the real data, where we use the discriminator only to specify the statistics that we think are worth matching. Specifically, we train the generator to match the expected value of the features on an intermediate layer of the discriminator. This is a natural choice of statistics for the generator to match, since by training the discriminator we ask it to find those features that are most discriminative of real data versus data generated by the current model.

Letting f(x) denote activations on an intermediate layer of the discriminator, our new objective for the generator is defined as: ||𝔼_(x∼p_(data)) f(x) − 𝔼_(z∼p_z(z))f(G(z))||²₂. The discriminator, and hence f(x), are trained as with vanilla GANs. As with regular GAN training, the objective has a fixed point where G exactly matches the distribution of training data.

PaperSourceSee Code · eli5168/improved_gan_pytorch

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: Feature Matching Selector (FMS); Sparse-to-dense Feature Matching; 3D-Aware GANs with Template Feature Field; Exact Feature Distribution Matching (EFDM); Cascade feature Matching TRansformer (CasMTR); Spectrum-Balanced Feature Matching (SpecMatch); NON-ADVERSARIAL INVERSE REINFORCEMENT LEARNING VIA SUCCESSOR FEATURE MATCHING; Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps.

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: 16 · with a code link: 9 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3 of 16 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 16 of 16, 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 35 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
Generative Adversarial Network3
Image Generation3
Attribute2
Conditional Image Generation2
Image Inpainting2
3D Medical Imaging Segmentation1
Appearance Transfer1
Brain Image Segmentation1
Brain Segmentation1
Data Augmentation1
Deblurring1
Dimensionality Reduction1
Face Generation1
Face Recognition1
Facial Inpainting1
Few-Shot Semantic Segmentation1
Fine-Grained Image Inpainting1
General Classification1
Image Segmentation1
Image-to-Image Translation1

Usage over time archive 2025-07-28

Papers per year tagged with GAN Feature Matching: 2016 to 2023, peak 5 5 0 2016: 1 paper 2016 2017: 3 papers 2017 2018: 5 papers 2018 2019: 1 paper 2019 2020: 4 papers 2020 2021: 1 paper 2021 2022: 0 papers 2022 2023: 1 paper 2023
Papers per year the archive tags with this method, by the paper's archive date (16 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

Regularization

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