Papers › Conditional Image Synthesis With Auxiliary Classifier GANs

Conditional Image Synthesis With Auxiliary Classifier GANs

30 Oct 2016ICML 2017 8arXiv:1610.09585archive 2025-07-28

Augustus Odena, Christopher Olah, Jonathon Shlens

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128x128 samples are more than twice as discriminable as artificially resized 32x32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1610.09585")

Code

Syntology Ran 5 of 5 code samples harvested from 3 repositories linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 5 samples from 3 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

37 repositories listed; official and paper-mentioned ones first.

2xic/notebooks mentioned on GitHub report
Byte7/GANs mentioned on GitHub report
Callifrey/ACGAN-Paddle mentioned on GitHubpaddle report
Hydrino/ACGAN_cifar10 mentioned on GitHubpytorch report
Hydrino/ACGAN_mnist mentioned on GitHubpytorch report
Mckinsey666/ACGAN-Anime-Generation mentioned on GitHubpytorch report
Mckinsey666/Anime-Generation mentioned on GitHubpytorch report
Ram81/AC-VAEGAN-PyTorch mentioned on GitHubpytorch report
VitoRazor/Gan_Architecture mentioned on GitHubtfGPL-3.0 report
ZhimingZhou/AM-GAN mentioned on GitHubtf report
asprenger/keras_acgan mentioned on GitHubtf report
bunny98/Text-to-Image-Using-GAN mentioned on GitHubtfGPL-3.0 report
buriburisuri/ac-gan mentioned on GitHubtf report
clvrai/ACGAN-PyTorch mentioned on GitHubpytorch report
dacostaHugo/AC-GANs mentioned on GitHub report
dashayushman/TAC-GAN mentioned on GitHubtf report
eriklindernoren/PyTorch-GAN mentioned on GitHubpytorch report
facebookresearch/pytorch_GAN_zoo mentioned on GitHubpytorch report
gitlimlab/ACGAN-PyTorch mentioned on GitHubpytorch report
jackyjsy/ACWGAN mentioned on GitHubpytorch report
johnnyjana730/ACGAN_animate mentioned on GitHub report
kaonashi-tyc/zi2zi mentioned on GitHubtfApache-2.0 report
lonce/sonyGanFork mentioned on GitHubpytorch report
lukedeo/keras-acgan mentioned on GitHubtf report
lvyufeng/MindSpore-GAN mentioned on GitHubmindsporeMIT report
nocotan/pytorch-lightning-gans mentioned on GitHubpytorch report
pranavbudhwant/ACVAEGAN mentioned on GitHubpytorch report
runoguler/Aux-GAN mentioned on GitHubpytorch report
shpda/text-to-image-gen-model-acgan mentioned on GitHubpytorch report
takuhirok/CP-GAN mentioned on GitHubpytorchMIT report
takuhirok/rGAN mentioned on GitHubpytorchMIT report
zcemycl/Matlab-GAN mentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

5 samples harvested; 5 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it

Licence: 5 of the 5 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

calculate_frechet_distance shpda/text-to-image-gen-model-acgan/fid_calculator/fid_score.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 4cee7c1861294d59 · report
denorm_img johnnyjana730/ACGAN_animate/ACGAN_animate_main_3.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · 6f02ad5e6d0837dc · report
get_one_hot_targets dashayushman/TAC-GAN/dataprep.py community (archive-listed) ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 4d1e3c64982eab04 · report
norm_img johnnyjana730/ACGAN_animate/ACGAN_animate_main_3.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · b550bf3e1a49e6fe · report
one_hot_encode_str_lbl dashayushman/TAC-GAN/dataprep.py community (archive-listed) ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 397670394fa5a63a · report

Tasks

Conditional Image GenerationDiversityImage GenerationImage Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation CIFAR-10 AC-GAN Inception score 8.25 #20 of 25 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 AC-GAN Inception score 28.5 #22 of 22 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.

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