Papers › Exposing flaws of generative model evaluation metrics and their unfair treatment of...

Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

7 Jun 2023NeurIPS 2023 11arXiv:2306.04675archive 2025-07-28

George Stein, Jesse C. Cresswell, Rasa Hosseinzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Zhaoyan Liu, Anthony L. Caterini, J. Eric T. Taylor, Gabriel Loaiza-Ganem

We systematically study a wide variety of generative models spanning semantically-diverse image datasets to understand and improve the feature extractors and metrics used to evaluate them. Using best practices in psychophysics, we measure human perception of image realism for generated samples by conducting the largest experiment evaluating generative models to date, and find that no existing metric strongly correlates with human evaluations. Comparing to 17 modern metrics for evaluating the overall performance, fidelity, diversity, rarity, and memorization of generative models, we find that the state-of-the-art perceptual realism of diffusion models as judged by humans is not reflected in commonly reported metrics such as FID. This discrepancy is not explained by diversity in generated samples, though one cause is over-reliance on Inception-V3. We address these flaws through a study of alternative self-supervised feature extractors, find that the semantic information encoded by individual networks strongly depends on their training procedure, and show that DINOv2-ViT-L/14 allows for much richer evaluation of generative models. Next, we investigate data memorization, and find that generative models do memorize training examples on simple, smaller datasets like CIFAR10, but not necessarily on more complex datasets like ImageNet. However, our experiments show that current metrics do not properly detect memorization: none in the literature is able to separate memorization from other phenomena such as underfitting or mode shrinkage. To facilitate further development of generative models and their evaluation we release all generated image datasets, human evaluation data, and a modular library to compute 17 common metrics for 9 different encoders at https://github.com/layer6ai-labs/dgm-eval.

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 63 code samples: 62 from 8 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 63: 53 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 6 honoured, 1 violated, 23 with no contract checked; 23 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 18 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 59 samples from 7 repositories, 50 ran (30 with no instrument failure; 20 where Syntology's instrument failed); 1 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.

No sample is linked to this paper from 13 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. 14 of the 53 samples that ran have no recorded date.

layer6ai-labs/dgm-eval officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
gmum/PALATE mentioned on GitHubjaxSyntology: not harvested report
layer6ai-labs/dgm_manifold_survey mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New... (arXiv:2404.02954; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
louaaron/scaling-riemannian-diffusion mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Riemannian Diffusion Models (arXiv:2310.20030; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 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

63 samples harvested: 53 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 6 honoured, 1 violated, 23 with no contract checked; 23 where Syntology's instrument failed) · 10 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.

6ran · honoured contract
1ran · violated contract
18ran · our draft was wrong
5ran; the contract check could not run
23ran
10unverified

Licence: 12 of the 63 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 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 8 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. 1 sample is 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”. “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.

layer6ai-labs/dgm-eval official repository 3 samples, 2 ran (2 instrument-failed) · 1 unverified
get_dataloader_from_path dgm_eval/__main__.py ran · our draft was wrong MIT (permissive) · de1462c410a454f6 · report fixture: returned list · level recorded 2026-09-22
get_device_and_num_workers dgm_eval/__main__.py ran · our draft was wrong fingerprinted MIT (permissive) · 0e74fdd296ca6e73 · report fixture: signature device:NoneType/0/?, num_workers:NoneType/0/? · returned tuple · level recorded 2026-09-22
compute_representations in 6 papers dgm_eval/__main__.py unverified MIT (permissive) · 2bbe398e90e76c2d · report
rtqichen/residual-flows found in paper text by Syntology 7 samples, 7 ran (6 instrument-failed) · 0 unverified
geometric_logprob in 5 papers qualitative_samples.py ran · our draft was wrong fingerprinted MIT (permissive) · 3e0a8dc623475d8e · report fixture: signature ns:Tensor/2/float, p:Tensor/2/float · returned Tensor · level recorded, date not recorded
basic_logdet_estimator resflows/layers/iresblock.py ran · our draft was wrong MIT (permissive) · 9b16691c6712e596 · report fixture: signature g:Tensor/2/float, x:Tensor/2/float, n_power_series:int/0/int, vareps:Tensor/2/float, coeff_fn:callable/0/?, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
batch_jacobian in 9 papers resflows/layers/iresblock.py ran · our draft was wrong MIT (permissive) · 85a4b5aac95f359d · report fixture: signature g:Tensor/2/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
batch_trace resflows/layers/iresblock.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 70b3429a213d3584 · report fixture: signature M:Tensor/3/float · returned Tensor · level recorded 2026-09-22
count_parameters in 278 papers train_toy.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
standard_normal_logprob in 14 papers qualitative_samples.py ran · our draft was wrong fingerprinted MIT (permissive) · 2dc23e3f121c6a38 · report fixture: signature z:Tensor/2/float · returned Tensor · level recorded, date not recorded
standard_normal_sample in 7 papers qualitative_samples.py ran · our draft was wrong MIT (permissive) · 2168d015a2e457cb · report fixture: signature size:tuple/1/int · returned Tensor · level recorded, date not recorded
google-research/maskgit found in paper text by Syntology 14 samples, 12 ran (0 instrument-failed) · 2 unverified
apply_label_smoothing in 5 papers maskgit/libml/losses.py ran fingerprinted Apache-2.0 (permissive) · 1b2e0a7656cc76a7 · report fixture: signature one_hot_targets:ArrayImpl/2/float, label_smoothing:float/0/float · returned ArrayImpl · level recorded 2026-09-26
get_hyper in 8 papers maskgit/configs/base_config.py ran Apache-2.0 (permissive) · ffc38a27fd9393ba · report fixture: signature h:MockHyperparameter/0/? · returned list · level recorded 2026-09-24
get_hyper in 8 papers maskgit/configs/maskgit_class_cond_config.py ran Apache-2.0 (permissive) · 7dfd4d71b4b83843 · report fixture: signature h:HyperparameterConfig/0/? · returned dict · level recorded 2026-09-24
get_hyper in 8 papers maskgit/configs/vqgan_config.py ran Apache-2.0 (permissive) · cd108d44d16c6e3c · report fixture: signature h:MockHyperObject/0/? · returned dict · level recorded 2026-09-26
get_norm_layer in 111 papers maskgit/nets/layers.py ran Apache-2.0 (permissive) · 1983d19e3e1ab60d · report fixture: signature train:bool/0/bool, dtype:callable/0/?, norm_type:str/0/str · returned partial · level recorded 2026-09-26
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
maskgit/libml/losses.py ran fingerprinted Apache-2.0 (permissive) · 06f87811f5c2b96a · report fixture: signature y_true:ArrayImpl/2/float, y_pred:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
restore_from_path maskgit/utils.py ran Apache-2.0 (permissive) · 95c51644bf3cb9ff · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
schedule in 32 papers maskgit/libml/mask_schedule.py ran Apache-2.0 (permissive) · 877afab065f859ba · report fixture: signature ratio:float/0/float, total_unknown:int/0/int, method:str/0/str · returned ArrayImpl · level recorded 2026-09-26
squared_euclidean_distance maskgit/libml/losses.py ran Apache-2.0 (permissive) · d80134d1097de9c4 · report fixture: signature a:ArrayImpl/2/float, b:ArrayImpl/2/float, b2:ArrayImpl/2/float, precision:NoneType/0/? · returned ArrayImpl · level recorded 2026-09-26
tensorflow_style_avg_pooling maskgit/nets/layers.py ran Apache-2.0 (permissive) · 38e696a22dc81a6f · report fixture: signature x:ArrayImpl/4/float, window_shape:tuple/1/int, strides:tuple/1/int, padding:str/0/str · returned ArrayImpl · level recorded 2026-09-26
truncated_normal in 12 papers maskgit/nets/maskgit_transformer.py ran Apache-2.0 (permissive) · 0408240381821d2c · report fixture: signature stddev:float/0/float, dtype:callable/0/? · returned function · level recorded 2026-09-26
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
maskgit/nets/layers.py ran Apache-2.0 (permissive) · 5829218c5489c6b6 · report fixture: signature x:ArrayImpl/4/float, factor:int/0/int · returned ArrayImpl · level recorded 2026-09-26
mask_by_random_topk in 5 papers maskgit/libml/parallel_decode.py unverified Apache-2.0 (permissive) · 389c62669d4417ea · report
read_image_from_url maskgit/utils.py unverified Apache-2.0 (permissive) · e39a123f00eb58cd · report
Rayhane-mamah/Efficient-VDVAE found in paper text by Syntology 4 samples, 4 ran (0 instrument-failed) · 0 unverified
beta_softplus efficient_vdvae_jax/model/latent_layers.py ran fingerprinted MIT (permissive) · 9bd8ee32e810e900 · report fixture: signature x:ArrayImpl/2/float, beta:float/0/float · returned ArrayImpl · level recorded 2026-09-26
get_lr_schedule in 8 papers efficient_vdvae_jax/model/schedules.py ran MIT (permissive) · 8c4274c2f8994da8 · report fixture: signature decay_scheme:str/0/str, init_lr:float/0/float, warmup_steps:int/0/int, decay_steps:int/0/int, decay_rate:float/0/float, decay_start:int/0/int, min_lr:float/0/float · returned NarrowCosineDecay · level recorded 2026-09-26
stable_init efficient_vdvae_jax/model/conv2d.py ran MIT (permissive) · d177a0713d0bea82 · report fixture: signature scale:float/0/float, dtype:callable/0/? · returned function · level recorded 2026-09-26
uniform_init in 10 papers efficient_vdvae_jax/model/conv2d.py ran MIT (permissive) · 0f49a2b0642d1098 · report fixture: signature minval:float/0/float, maxval:float/0/float, dtype:callable/0/? · returned function · level recorded 2026-09-26
autonomousvision/projected-gan found in paper text by Syntology 2 samples, 2 ran (0 instrument-failed) · 0 unverified
parse_range in 22 papers gen_video.py ran · honoured contract MIT (permissive) · 025e4c7cda618f25 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-22
parse_tuple in 34 papers gen_video.py ran MIT (permissive) · 6a0f2095bdd516ab · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-26
SHI-Labs/StyleNAT found in paper text by Syntology 12 samples, 8 ran (3 instrument-failed) · 4 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/generator.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
data_sampler in 17 papers dataset/dataset.py ran MIT (permissive) · 258c1af08f41aa17 · report fixture: signature dataset:SimpleDataset/0/?, shuffle:bool/0/bool, distributed:bool/0/bool · returned RandomSampler · level recorded 2026-09-26
get_haar_wavelet models/discriminator.py ran fingerprinted MIT (permissive) · 9865a02804b0266f · report fixture: signature in_channels:int/0/int · returned tuple · level recorded 2026-09-26
make_kernel in 34 papers models/basic_layers.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
unnormalize in 21 papers dataset/dataset.py ran fingerprinted MIT (permissive) · 43108d105300b7f5 · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-26
unswin_window src/analysis.py ran MIT (permissive) · 001e240d5a8fc4dc · report fixture: signature q0:Tensor/4/float, q1:Tensor/4/float, k0:Tensor/4/float, k1:Tensor/4/float, hw:int/0/int, ws:int/0/int, nheads:int/0/int · returned Tensor · level recorded 2026-09-26
upfirdn2d_native in 26 papers
census: 5 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
op/upfirdn2d.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · fe99cfd294676edb · report fixture: signature input:Tensor/4/float, kernel:Tensor/2/float, up_x:int/0/int, up_y:int/0/int, down_x:int/0/int, down_y:int/0/int, pad_x0:int/0/int, pad_x1:int/0/int, pad_y0:int/0/int, pad_y1:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/generator.py ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
add_watermark src/inference.py unverified MIT (permissive) · da365dda2e5af8e0 · report
calculate_activation_statistics in 75 papers utils/fid_score.py unverified MIT (permissive) · 12b482fc759f87dd · report
calculate_frechet_distance in 119 papers utils/fid_score.py unverified MIT (permissive) · 0def50a351111624 · report
get_activations in 100 papers utils/fid_score.py unverified MIT (permissive) · c1f9693596855557 · report
Zhendong-Wang/Diffusion-GAN found in paper text by Syntology 19 samples, 17 ran (11 instrument-failed) · 2 unverified
parse_tuple in 34 papers diffusion-projected-gan/dataset_tool.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 9cd07419f7c926f8 · report fixture: signature s:str/0/str · returned tuple · level recorded, date not recorded
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
diffusion-projected-gan/pg_modules/diffaug.py ran fingerprinted MIT (permissive) · da4e9834e767ce2d · report fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded 2026-09-26
NormLayer in 13 papers diffusion-projected-gan/pg_modules/blocks.py ran · our draft was wrong MIT (permissive) · ef1e7dffb5d433d4 · report fixture: signature c:int/0/int, mode:str/0/str · returned BatchNorm2d · level recorded 2026-09-22
UpBlockBig in 6 papers diffusion-projected-gan/pg_modules/blocks.py ran · our draft was wrong MIT (permissive) · f87cd99314206f72 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-24
UpBlockSmall in 6 papers diffusion-projected-gan/pg_modules/blocks.py ran · our draft was wrong MIT (permissive) · 0186912dcb8b92b9 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-24
file_ext in 37 papers diffusion-projected-gan/dataset_tool.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
format_time in 140 papers diffusion-projected-gan/dnnlib/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 053fc534bc6bb989 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-25
format_time_brief in 69 papers diffusion-projected-gan/dnnlib/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 77f4aa0649e7f404 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-25
layout_grid in 7 papers diffusion-projected-gan/gen_video.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 456c172851946697 · report fixture: signature img:Tensor/4/float, grid_w:NoneType/0/?, grid_h:int/0/int, float_to_uint8:bool/0/bool, chw_to_hwc:bool/0/bool, to_numpy:bool/0/bool · returned ndarray · level recorded 2026-09-22
make_transform in 17 papers diffusion-projected-gan/gen_images.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted MIT (permissive) · f47dff4b7b27bba7 · report fixture: signature translate:tuple/1/float, angle:float/0/float · returned ndarray · level recorded 2026-09-22
maybe_min in 36 papers diffusion-projected-gan/dataset_tool.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
normalize_second_moment diffusion-projected-gan/pg_modules/networks_fastgan.py ran fingerprinted MIT (permissive) · 02870cd90e053ab0 · report fixture: signature x:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-26
parse_comma_separated_list in 14 papers diffusion-projected-gan/calc_metrics.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · d01b68a634f71551 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
parse_range in 22 papers diffusion-projected-gan/gen_images.py ran · honoured contract MIT (permissive) · 236de8614a178382 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-22
parse_vec2 in 12 papers diffusion-projected-gan/gen_images.py ran · honoured contract MIT (permissive) · 180016b9227381b1 · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-22
rand_brightness in 25 papers
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
diffusion-projected-gan/pg_modules/diffaug.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 011230b2b9b8fb6f · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
rand_saturation in 24 papers
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
diffusion-projected-gan/pg_modules/diffaug.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 5b0d8787e670fc63 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
ask_yes_no in 70 papers diffusion-projected-gan/dnnlib/util.py unverified MIT (permissive) · 9d31d2c4cd16bb2d · report
compute_is in 10 papers diffusion-projected-gan/metrics/inception_score.py unverified MIT (permissive) here; the stored copy is pointer only · fc49fa553c005268 · report
sbarratt/inception-score-pytorch found in paper text by Syntology 1 sample, 0 ran · 1 unverified
inception_score in 13 papers inception_score.py unverified MIT (permissive) · 6d3c813b7561493d · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is 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.
chunk in 52 papers repository not located ran · our draft was wrong licence of this copy not recorded · 8241c0562bc710fd · report fixture: signature it:list/1/int, size:int/0/int · returned callable_iterator · level recorded, date not recorded

Tasks

DiversityImage GenerationMemorization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) Coverage 0.71 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) Density 0.77 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) FD 229.42 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) FID 2.11 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) Precision 0.79 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleNAT (Exposing) Recall 0.41 #3 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) Coverage 0.63 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) Density 0.68 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) FD 240.07 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) FID 2.26 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) Precision 0.77 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN-XL (Exposing) Recall 0.43 #5 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) Coverage 0.64 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) Density 0.71 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) FD 303.21 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) FID 2.89 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) Precision 0.79 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleSwin (Exposing) Recall 0.28 #11 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 InsGen (Exposing) Coverage 0.51 #18 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 InsGen (Exposing) FD 436.26 #18 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 InsGen (Exposing) FID 3.46 #18 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 InsGen (Exposing) Precision 0.64 #18 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 InsGen (Exposing) Recall 0.13 #18 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) Coverage 0.30 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) Density 0.31 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) FD 589.20 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) FID 4.29 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) Precision 0.57 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Projected-GAN (Exposing) Recall 0.07 #21 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) Coverage 0.39 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) Density 0.36 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) FD 514.78 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) FID 5.30 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) Precision 0.59 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 StyleGAN2-ada (Exposing) Recall 0.06 #26 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) Coverage 0.74 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) Density 0.83 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) FD 226.72 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) FID 8.11 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) Precision 0.81 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 LDM (Exposing) Recall 0.44 #32 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) Coverage 0.53 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) Density 0.61 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) FD 393.45 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) FID 9.02 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) Precision 0.76 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Unleash-Trans (Exposing) Recall 0.24 #34 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) Coverage 0.54 #39 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) Density 1.04 #39 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) FD 514.16 #39 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) FID 34.88 #39 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) Precision 0.86 #39 of 51 Archive leaderboard report
Image Generation FFHQ 256 x 256 Efficient-vdVAE (Exposing) Recall 0.14 #39 of 51 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

Diffusion

1 archive method tag without a method page not shown.

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