Papers › Projected GANs Converge Faster
Projected GANs Converge Faster
Axel Sauer, Kashyap Chitta, Jens Müller, Andreas Geiger
Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. Our Projected GAN improves image quality, sample efficiency, and convergence speed. It is further compatible with resolutions of up to one Megapixel and advances the state-of-the-art Fréchet Inception Distance (FID) on twenty-two benchmark datasets. Importantly, Projected GANs match the previously lowest FIDs up to 40 times faster, cutting the wall-clock time from 5 days to less than 3 hours given the same computational resources.
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="2111.01007")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2111.01007", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2111.01007")
Code
Syntology 49 code samples: 44 from 3 repositories linked to this paper, 5 identical to code harvested from another paper's repository. Across all 49: 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 17 samples from 1 repository, 12 ran (6 with no instrument failure; 6 where Syntology's instrument failed); community (archive-listed): 27 samples from 2 repositories, 21 ran (14 with no instrument failure; 7 where Syntology's instrument failed); 5 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 38 samples that ran have no recorded date.
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.
Code Syntology ran Syntology
49 samples harvested: 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 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: 6 of the 49 samples are 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 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. 5 samples are listed last, in a group without a repository. “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 9 samples that ran, the graph records a signature this page does not show: 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. “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: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 pg_modules/discriminator.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) ·
fb2ae62e229d8e49 · report
fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded 2026-09-22 be3ac00fad675c3d · report
fixture: returned DownBlock · level recorded 2026-09-22 2698386cbe6cddd4 · report
fixture: returned DownBlockPatch · level recorded 2026-09-22 d594247fe0a8ac63 · report
fixture: returned FeatureFusionBlock · level recorded 2026-09-22 ef1e7dffb5d433d4 · report
fixture: signature c:int/0/int, mode:str/0/str · returned BatchNorm2d · level recorded 2026-09-22 537c69fac8de5c08 · report
fixture: returned SeparableConv2d · level recorded 2026-09-22 012485a042fbe914 · report
fixture: returned SingleDisc · level recorded 2026-09-22 6e9fa10927d234c5 · report
fixture: signature model:callable/0/? · returned Module · level recorded 2026-09-22 34b8baa98458240a · report
fixture: signature scratch:Scratch/0/?, in_channels:list/1/int, cout:int/0/int, expand:bool/0/bool · returned Scratch · level recorded 2026-09-22 022a2fd988863842 · report
fixture: signature scratch:ScratchStandIn/0/?, in_channels:list/1/int, cout:int/0/int, expand:bool/0/bool · returned ScratchStandIn · level recorded 2026-09-22 d1223b5ae8d2262a · report
fixture: signature pretrained:callable/0/?, inp_res:int/0/int · returned list · level recorded 2026-09-22 census: 6 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 pg_modules/discriminator.py ran · our draft was wrong fingerprinted MIT (permissive) ·
ad4806edfa54ef28 · report
fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22 c3ff68174f3a9086 · report
aa08964cb4a41f68 · report
fixture: returned CSM · level recorded 2026-09-22 census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket projected_gan.py ran MIT (permissive) ·
fb73f5657d3d5dfd · report
fixture: returned DiffAugment · level recorded 2026-09-22 93f4a2947c32908b · report
fixture: returned DownBlock · level recorded 2026-09-22 a7241f6b2a584c67 · report
fixture: returned EfficientNetLite · level recorded 2026-09-22 daa6b7ac4d6d0dfe · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 860a49493f25946b · report
fixture: returned Generator · level recorded 2026-09-22 c020e77bd5b82cc6 · report
fixture: returned InitLayer · level recorded 2026-09-22 d65e8029380ee87d · report
fixture: returned MBConvBlock · level recorded 2026-09-22 c102280a98c32877 · report
fixture: returned MultiScaleDiscriminator · level recorded 2026-09-22 9a620288c91dd5f1 · report
fixture: signature feat:Tensor/4/float, noise:NoneType/0/? · returned Tensor · level recorded 2026-09-24 3ee6dbc09a4b76ac · report
fixture: returned SEBlock · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 projected_gan.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) ·
396c57f5f6d8edd7 · report
fixture: signature feat:Tensor/2/float · returned Tensor · level recorded 2026-09-22 32d6c5741cfd6028 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-22 d8f6aa2842cb7bc6 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-22 83ae32deb9c6d5eb · report
fixture: signature num_features:int/0/int · returned BatchNorm2d · level recorded 2026-09-22 d840598eafed7a9d · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, groups:int/0/int, bias:bool/0/bool, padding_mode:str/0/str · returned Conv2d · level recorded 2026-09-22 b27240435837ab3d · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, output_padding:int/0/int, groups:int/0/int, bias:bool/0/bool, dilation:int/0/int, padding_mode:str/0/str · returned ConvTranspose2d · level recorded 2026-09-22 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 projected_gan.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) ·
ed953cd5fd3a44c8 · report
fixture: signature x:Tensor/4/float, drop_connect_rate:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 243747f15fce5ac8 · report
fixture: signature data_path:str/0/str, batch_size:int/0/int · returned DataLoader · level recorded 2026-09-22 1522c02775ece4c4 · report
fixture: signature filters:int/0/int, multiplier:float/0/float, divisor:int/0/int, min_width:int/0/int · returned int · level recorded 2026-09-22 b5099ac2f4a497ef · report
fixture: signature repeats:int/0/int, multiplier:float/0/float · returned int · level recorded 2026-09-22 0754baca942753a6 · report
41472db28a1d6bb6 · report
5 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded ·
011230b2b9b8fb6f · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded ·
cf3f99cfbe8f451a · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 census: 6 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded ·
8a8f1bb31f56eb41 · report
fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22 census: 6 implementations from 9 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded ·
5b0d8787e670fc63 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded 64f17a01e2d642b0 · report
fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22 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.
3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
3 sibling assemblies for Projected GAN (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Projected GAN (graph method: Projected GAN). 31 bricks; individually on a fixture: 26 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- ProjectedGAN entry · level 0 · unverified ·
d133245b208a1c3b - CSM model · level 1 · ran ·
aa08964cb4a41f68 - DiffAugment helper · level 1 · ran ·
fb73f5657d3d5dfd - Generator model · level 1 · ran ·
860a49493f25946b - MultiScaleDiscriminator model · level 1 · ran ·
c102280a98c32877 - build_efficientnet_lite helper · level 0 · unverified ·
e1b3d8c3301b619a - load_checkpoint helper · level 0 · unverified ·
0754baca942753a6 - load_data helper · level 1 · ran · our draft was wrong ·
243747f15fce5ac8 - kaiming_init helper · level 0 · unverified ·
b1c1a8a6e7a54d45 - InitLayer helper · level 1 · ran ·
c020e77bd5b82cc6 - SEBlock helper · level 1 · ran ·
3ee6dbc09a4b76ac - UpBlock helper · level 1 · ran · our draft was wrong ·
32d6c5741cfd6028 - UpBlockComp helper · level 1 · ran · our draft was wrong ·
d8f6aa2842cb7bc6 - conv2d helper · level 1 · ran · our draft was wrong ·
d840598eafed7a9d - weights_init helper · level 0 · unverified ·
0fb299a87938eec8 - DownBlock helper · level 1 · ran ·
93f4a2947c32908b - EfficientNetLite helper · level 1 · ran ·
a7241f6b2a584c67 - GLU helper · level 1 · ran ·
daa6b7ac4d6d0dfe - batchNorm2d helper · level 1 · ran · our draft was wrong ·
83ae32deb9c6d5eb - convTranspose2d helper · level 1 · ran · our draft was wrong ·
b27240435837ab3d - Swish helper · level 1 · ran ·
396c57f5f6d8edd7 - NoiseInjection helper · level 1 · ran ·
9a620288c91dd5f1 - MBConvBlock helper · level 1 · ran ·
d65e8029380ee87d - round_filters helper · level 1 · ran · honoured contract ·
1522c02775ece4c4 - round_repeats helper · level 1 · ran · honoured contract ·
b5099ac2f4a497ef - drop_connect helper · level 1 · ran; the contract check could not run (RAISES) ·
ed953cd5fd3a44c8 - rand_brightness helper · level 1 · ran · our draft was wrong ·
011230b2b9b8fb6f - rand_contrast helper · level 1 · ran; the contract check could not run (RAISES) ·
cf3f99cfbe8f451a - rand_cutout helper · level 1 · ran; the contract check could not run (RAISES) ·
8a8f1bb31f56eb41 - rand_saturation helper · level 1 · ran · our draft was wrong ·
5b0d8787e670fc63 - rand_translation helper · level 1 · ran; the contract check could not run (RAISES) ·
64f17a01e2d642b0
harvested Assembly for Projected GAN (graph method: Projected GAN). 22 bricks; individually on a fixture: 17 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- ProjectedDiscriminator entry · level 0 · unverified ·
c3ff68174f3a9086 - DiffAugment helper · level 1 · ran; the contract check could not run (RAISES) ·
fb2ae62e229d8e49 - F_RandomProj model · level 0 · unverified ·
d50f654da1e833ff - MultiScaleD model · level 0 · unverified ·
c5ec5be19a01b214 - _make_projector model · level 0 · unverified ·
15479f3c367a9af9 - SingleDisc model · level 1 · ran ·
012485a042fbe914 - SingleDiscCond helper · level 0 · unverified ·
6b8d529b6b9a1c09 - _make_efficientnet helper · level 1 · ran · our draft was wrong ·
6e9fa10927d234c5 - _make_scratch_ccm helper · level 1 · ran; the contract check could not run (RAISES) ·
34b8baa98458240a - _make_scratch_csm helper · level 1 · ran; the contract check could not run (RAISES) ·
022a2fd988863842 - calc_channels helper · level 1 · ran · honoured contract ·
d1223b5ae8d2262a - DownBlock helper · level 1 · ran ·
be3ac00fad675c3d - DownBlockPatch helper · level 1 · ran ·
2698386cbe6cddd4 - conv2d helper · level 1 · ran · our draft was wrong ·
d840598eafed7a9d - FeatureFusionBlock helper · level 1 · ran ·
d594247fe0a8ac63 - NormLayer helper · level 1 · ran · our draft was wrong ·
ef1e7dffb5d433d4 - SeparableConv2d helper · level 1 · ran ·
537c69fac8de5c08 - rand_brightness helper · level 1 · ran · our draft was wrong ·
011230b2b9b8fb6f - rand_contrast helper · level 1 · ran; the contract check could not run (RAISES) ·
cf3f99cfbe8f451a - rand_cutout helper · level 1 · ran · our draft was wrong ·
ad4806edfa54ef28 - rand_saturation helper · level 1 · ran · our draft was wrong ·
5b0d8787e670fc63 - rand_translation helper · level 1 · ran; the contract check could not run ·
4cfe42eb20e188c9
harvested Assembly for Projected GAN (graph method: Projected GAN). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- Projector entry · level 0 · unverified ·
41472db28a1d6bb6
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="2111.01007") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
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.
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