Papers › Closed-Form Factorization of Latent Semantics in GANs

Closed-Form Factorization of Latent Semantics in GANs

13 Jul 2020CVPR 2021 1arXiv:2007.06600archive 2025-07-28

Yujun Shen, Bolei Zhou

A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In order to identify such latent dimensions for image editing, previous methods typically annotate a collection of synthesized samples and train linear classifiers in the latent space. However, they require a clear definition of the target attribute as well as the corresponding manual annotations, limiting their applications in practice. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. In particular, we take a closer look into the generation mechanism of GANs and further propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights. With a lightning-fast implementation, our approach is capable of not only finding semantically meaningful dimensions comparably to the state-of-the-art supervised methods, but also resulting in far more versatile concepts across multiple GAN models trained on a wide range of datasets.

PaperPDFConference PDFCodeCode Syntology ran

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):

Code

Syntology 14 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 3 repositories, 13 ran (7 with no instrument failure; 6 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:

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. 1 of the 13 samples that ran has no recorded date.

HideUnderBush/UI2I_via_StyleGAN2 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
akashgit/stylegan2_wt mentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (4 instrument-failed) · 1 unverified report
dkn16/stylegan2-pytorch mentioned on GitHubpytorchSyntology: not harvested report
genforce/sefa mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
happy-jihye/Cartoon-StyleGAN mentioned on GitHubpytorchSyntology: not harvested report
happy-jihye/Cartoon-StyleGan2 mentioned on GitHubpytorchSyntology: not harvested report
kostagiolasn/Unsupervised-Discovery-of-Semantic-Concepts-in-Satellite-Imagery-with-Style-based-Wavelet-driven-Gen mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
kostagiolasn/satconcepts mentioned on GitHubpytorchMITSyntology: not harvested report
phymhan/stylegan2-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Analyzing and Improving the Image Quality of StyleGAN (arXiv:1912.04958; that paper's own run record: 68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified); nothing checks that they implement this paper's method. report
rosinality/stylegan2-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Analyzing and Improving the Image Quality of StyleGAN (arXiv:1912.04958; that paper's own run record: 68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified) and The Geometry of Deep Generative Image Models and its Applications (arXiv:2101.06006; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
woctezuma/steam-stylegan2 mentioned on GitHubpytorchMITSyntology: not harvested 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
2ran; the contract check could not run
5ran
1unverified

Licence: 2 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 3 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. 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.

akashgit/stylegan2_wt community (archive-listed) 10 samples, 9 ran (4 instrument-failed) · 1 unverified
all_gather in 119 papers distributed.py ran MIT (permissive) · ed03ba54397adbe4 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-26
calc_fid in 8 papers fid.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · e6c1de4697e7ed81 · report fixture: signature sample_mean:ndarray/1/float, sample_cov:ndarray/2/float, real_mean:ndarray/1/float, real_cov:ndarray/2/float, eps:float/0/float · returned float32 · level recorded 2026-09-22
convert_conv in 6 papers convert_weight.py ran · our draft was wrong MIT (permissive) · 7fe245a7216ae67b · report fixture: signature vars:MockVarsDict/0/?, source_name:str/0/str, target_name:str/0/str, bias:bool/0/bool, start:int/0/int · returned dict · level recorded 2026-09-22
convert_modconv in 5 papers convert_weight.py ran · our draft was wrong MIT (permissive) · 1c7cd5abc48bcf75 · report fixture: signature vars:dict/0/?, source_name:str/0/str, target_name:str/0/str, flip:bool/0/bool · returned dict · level recorded 2026-09-22
convert_torgb in 5 papers convert_weight.py ran · our draft was wrong MIT (permissive) · 96b279b9ef818d94 · report fixture: signature vars:dict/0/?, source_name:str/0/str, target_name:str/0/str · returned dict · level recorded 2026-09-22
extract_features in 73 papers calc_inception.py ran MIT (permissive) · 826a4bfd8b5cb2fc · report fixture: signature loader:list/1/Tensor, inception:callable/0/?, device:str/0/str · returned Tensor · level recorded 2026-09-25
make_kernel in 34 papers model.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 6f65e378a4313f87 · report fixture: signature k:list/1/float · returned Tensor · level recorded, date not recorded
reduce_loss_dict in 18 papers distributed.py ran MIT (permissive) · 5144ad456049f8ce · report fixture: signature loss_dict:dict/0/? · returned dict · level recorded 2026-09-26
reduce_sum in 34 papers
census: 4 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
distributed.py ran · honoured contract fingerprinted MIT (permissive) · 3f0a1105ef251d78 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
extract_feature_from_samples in 6 papers fid.py unverified MIT (permissive) · 7284618ab4d5847d · report
genforce/sefa community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
interface.py ran; the contract check could not run (RAISES) MIT (permissive) · c829d5c7718a2fb6 · report fixture: returned ndarray · level recorded 2026-09-22
kostagiolasn/Unsupervised-Discovery-of-Semantic-Concepts-in-Satellite-Imagery-with-Style-based-Wavelet-driven-Gen community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
make_image in 14 papers apply_factor.py ran fingerprinted MIT (permissive) · 3a06aea8ca067253 · report fixture: signature tensor:Tensor/4/float · returned ndarray · level recorded 2026-09-24
score_2afc_dataset in 18 papers lpips/dist_model.py ran · our draft was wrong MIT (permissive) · 514dd3c0eee3691c · report fixture: signature data_loader:CustomDatasetDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25
score_jnd_dataset in 10 papers lpips/dist_model.py ran MIT (permissive) · 581c80d602289d6d · report fixture: signature data_loader:MockDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25

Tasks

AttributeFormImage GenerationImage Manipulation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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