Papers › Spectral Normalization for Generative Adversarial Networks
Spectral Normalization for Generative Adversarial Networks
Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.
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.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1802.05957")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1802.05957", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1802.05957")
Code
The archive's official repository (pfnet-research/sngan_projection) was not harvested; the 31 samples below come from 19 repositories the archive does not mark official.
Syntology 31 code samples harvested from 19 repositories linked to this paper: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: named in the paper: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 30 samples from 18 repositories, 24 ran (20 with no instrument failure; 4 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 2 of its repositories that Syntology harvested for other papers:
- pytorch/pytorch, community (archive-listed): harvested for another paper, listed under the repository
- yangyucheng000/Paper-3, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
38 repositories listed; official and paper-mentioned ones first.
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
31 samples harvested: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 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.
Licence: 15 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 19 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”. For 4 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 3, for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket models/discriminators/resblocks.py ran fingerprinted MIT (permissive) ·
140b5bac7a8508a9 · report
fixture: returned Block · level recorded 2026-09-22 78f554911984ea8d · report
fixture: returned DenseSN · level recorded 2026-09-22 1618dd723285892b · report
fixture: returned DenseSN · level recorded 2026-09-22 ad0eca31b5e574c4 · report
64ebe64e3ec531c1 · report
fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-26 146991926013af84 · report
fixture: signature layer_type:str/0/str · returned partial · level recorded 2026-09-26 c4b9e0cb79abdf65 · report
fixture: signature file_name:str/0/str · returned dict · level recorded 2026-09-26 6c7988ea60c79ae4 · report
fixture: returned ndarray · level recorded 2026-09-26 86091e3080eadd73 · report
fixture: signature vector_tensor:Tensor/4/float · returned ndarray · level recorded 2026-09-26 07d08fa9cc777740 · report
fixture: signature init_type:str/0/str · returned function · level recorded 2026-09-26 463156b57378ec6e · report
f202366742ae57fc · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 eea0b4fc0256e64c · report
fixture: returned SpectralNorm · level recorded 2026-09-22 7a608922984c40b9 · report
fixture: signature v:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 cb5d0b5f94066d27 · report
95f6381171e5b22f · report
fixture: returned SpectralNorm · level recorded 2026-09-22 5c6f3d4b49c16aa5 · report
eee46d1790d3fc3d · report
fixture: returned SpectralNorm · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket datasets.py ran MIT (permissive) ·
128a565cc437a6cb · report
fixture: signature img_lab:ndarray/3/float · returned ndarray · level recorded 2026-09-26 census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket datasets.py ran fingerprinted MIT (permissive) ·
01d26fcf1d7994f7 · report
fixture: signature img_bgr:ndarray/3/int · returned ndarray · level recorded 2026-09-26 a01c9b17a6119a4a · report
fixture: signature file:str/0/str · returned dict · level recorded 2026-09-26 a587e964e3b73e7f · report
fixture: returned SpectralNorm · level recorded 2026-09-22 9b11458d7d1ec61c · report
fixture: signature v:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 e5baa0b3b62b8c9b · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 6ca4fd5871d2fad1 · report
fixture: signature weight:Tensor/2/float, u:Tensor/2/float, Ip:int/0/int · returned tuple · level recorded 2026-09-22 c11fdae8c1eaa067 · report
fixture: returned SpectralNorm · level recorded 2026-09-22 2ed2088d35626661 · report
fixture: returned SNLinear · level recorded 2026-09-22 census: 15 implementations from 13 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 sn_gan/sn_modules.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
bf5a05c7adc49b0b · report
fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 bedff51745d2cf84 · report
fixture: signature v:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 4d8feb46b282de73 · 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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
17 assemblies on this paper: 17 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
17 sibling assemblies for Spectral Normalization (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 17 sibling assemblies; the other 5 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
eee46d1790d3fc3d - SpectralNormLoadStateDictPreHook helper · level 0 · unverified ·
1e050801dc7eacb6 - SpectralNormStateDictHook helper · level 1 · ran ·
516e5546283f358b
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- DenseSN entry · level 1 · ran ·
1618dd723285892b
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
c11fdae8c1eaa067
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- SNLinear entry · level 1 · ran ·
e5baa0b3b62b8c9b - max_singular_value helper · level 1 · ran; the contract check could not run (RAISES) ·
6ca4fd5871d2fad1
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
43fb0d94c6f43e76
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
a587e964e3b73e7f - l2normalize helper · level 1 · ran · violated contract ·
9b11458d7d1ec61c
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
95f6381171e5b22f
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- SNLinear entry · level 1 · ran ·
2ed2088d35626661 - l2_normalize helper · level 1 · ran · our draft was wrong ·
bf5a05c7adc49b0b
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- Block entry · level 1 · ran ·
140b5bac7a8508a9
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- SpectralNorm entry · level 1 · ran ·
eea0b4fc0256e64c - l2normalize helper · level 1 · ran · our draft was wrong ·
bedff51745d2cf84
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- spectral_norm entry · level 0 · unverified ·
4d8feb46b282de73
harvested Assembly for Spectral Normalization (graph method: Spectral Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 17 siblings
- DenseSN entry · level 1 · ran ·
78f554911984ea8d
- SN · bdf8cca7ad832622 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- SpectralNorm · c197b879005531d3 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- SpectralNorm · cf445554e7fa5083 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- ResidualBlock · f080b2b541943893 · 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 · assemblies[15] in the JSON twin
- ResBlockDiscriminator · f1bb4ba090ed16e9 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
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="1802.05957") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | CIFAR-10 | SN-GANs | FID | 21.7 | #58 of 78 | Archive leaderboard | report |
| Image Generation | STL-10 | SN-GAN | FID | 40.1 | #26 of 31 | Archive leaderboard | report |
| Image Generation | STL-10 | SN-GAN | Inception score | 9.10 | #26 of 31 | 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
Introduced by this paper: SNGAN, Spectral Normalization
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