Papers › Feature Quantization Improves GAN Training

Feature Quantization Improves GAN Training

5 Apr 2020ICML 2020 1arXiv:2004.02088archive 2025-07-28

Yang Zhao, Chunyuan Li, Ping Yu, Jianfeng Gao, Changyou Chen

The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile balance between the fixed target distribution and the progressively generated distribution. In this work, we propose Feature Quantization (FQ) for the discriminator, to embed both true and fake data samples into a shared discrete space. The quantized values of FQ are constructed as an evolving dictionary, which is consistent with feature statistics of the recent distribution history. Hence, FQ implicitly enables robust feature matching in a compact space. Our method can be easily plugged into existing GAN models, with little computational overhead in training. We apply FQ to 3 representative GAN models on 9 benchmarks: BigGAN for image generation, StyleGAN for face synthesis, and U-GAT-IT for unsupervised image-to-image translation. Extensive experimental results show that the proposed FQ-GAN can improve the FID scores of baseline methods by a large margin on a variety of tasks, achieving new state-of-the-art performance.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of Feature Quantization (FQ), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Feature Quantization (FQ)') (how to connect); the free check have('2004.02088') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 4 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

YangNaruto/FQ-GAN officialmentioned in papermentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yangyucheng000/MSpaper mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Supervision Can Be a Good Few-Shot Learner (arXiv:2207.09176; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran
1unverified

Licence: 1 of the 4 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

YangNaruto/FQ-GAN official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Quantize FQ-BigGAN/vq_layer.py ran no licence file found · pointer only · 0be995ce42c516e0 · report fixture: signature x:Tensor/4/float, y:NoneType/0/? · returned tuple · level recorded 2026-09-22
taki0112/UGATIT found in paper text by Syntology 3 samples, 2 ran (0 instrument-failed) · 1 unverified
load_test_data in 21 papers utils.py ran MIT (permissive) · dcce1222c3697159 · report fixture: signature image_path:str/0/str, size:int/0/int · returned ndarray · level recorded 2026-09-25
save_images in 24 papers utils.py ran MIT (permissive) · dfa35c437d3cf0d5 · report fixture: signature images:ndarray/4/float, size:tuple/1/int, image_path:str/0/str · returned bool · level recorded 2026-09-25
augmentation in 17 papers utils.py unverified MIT (permissive) · 76abd03df3e34279 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Feature Quantization (FQ) (graph method: Feature Quantization (FQ)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 6 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. feature_quantization_nearest_neighbor entry · level 3 · ran · violated contract · 0419ccec451a255e0accdbd463999985d2b635c689751bd4dac0d7cbeabe387e

harvested Assembly for Feature Quantization (FQ) (graph method: Feature Quantization (FQ)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. Quantize entry · level 1 · ran · 0be995ce42c516e0

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2004.02088") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationFace GenerationImage GenerationImage-to-Image TranslationQuantizationTranslationUnsupervised Image-To-Image Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation CIFAR-10 FQ-GAN FID 5.34 #6 of 25 Archive leaderboard report
Conditional Image Generation CIFAR-10 FQ-GAN Inception score 8.50 #6 of 25 Archive leaderboard report
Conditional Image Generation CIFAR-100 FQ-GAN FID 7.15 #2 of 7 Archive leaderboard report
Conditional Image Generation CIFAR-100 FQ-GAN Inception Score 9.74 #2 of 7 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 FQ-GAN FID 13.77 #17 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 FQ-GAN Inception score 54.36 #17 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 64x64 FQ-GAN FID 9.67 #3 of 4 Archive leaderboard report
Conditional Image Generation ImageNet 64x64 FQ-GAN Inception score 25.96 #3 of 4 Archive leaderboard report
Image Generation FFHQ 1024 x 1024 FQ-GAN FID 3.19 #9 of 20 Archive leaderboard report
Image-to-Image Translation anime-to-selfie FQ-GAN Kernel Inception Distance 10.23 #1 of 2 Archive leaderboard report
Image-to-Image Translation selfie-to-anime FQ-GAN Kernel Inception Distance 11.40 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAdamAdaptive Instance NormalizationBatch NormalizationBigGANConditional Batch NormalizationConvolutionDense ConnectionsEarly StoppingFeedforward NetworkGAN Feature MatchingGAN Hinge LossLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationProjection DiscriminatorR1 RegularizationReLUResidual BlockResidual ConnectionSAGANSoftmaxSpectral NormalizationStyleGANTTURTruncation Trick

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