Papers › Assessing Generative Models via Precision and Recall

Assessing Generative Models via Precision and Recall

31 May 2018NeurIPS 2018 12arXiv:1806.00035archive 2025-07-28

Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly

Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as the Frechet Inception Distance (FID), correlate well with the perceived quality of samples and are sensitive to mode dropping. However, these metrics are unable to distinguish between different failure cases since they only yield one-dimensional scores. We propose a novel definition of precision and recall for distributions which disentangles the divergence into two separate dimensions. The proposed notion is intuitive, retains desirable properties, and naturally leads to an efficient algorithm that can be used to evaluate generative models. We relate this notion to total variation as well as to recent evaluation metrics such as Inception Score and FID. To demonstrate the practical utility of the proposed approach we perform an empirical study on several variants of Generative Adversarial Networks and Variational Autoencoders. In an extensive set of experiments we show that the proposed metric is able to disentangle the quality of generated samples from the coverage of the target distribution.

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 15 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 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, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 7 ran (6 with no instrument failure; 1 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.

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.

msmsajjadi/precision-recall-distributions officialmentioned in papermentioned on GitHubtfSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
ok1zjf/lbae mentioned on GitHubpytorchMITSyntology: 12 samples, 7 ran (1 instrument-failed) · 5 unverified report
raahii/evan mentioned on GitHubpytorchSyntology: not harvested report
raahii/video-gans-evaluation mentioned on GitHubpytorchSyntology: 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.

Code Syntology ran Syntology

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

4ran; the contract check could not run
6ran
5unverified

Licence: 0 of the 15 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 2 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.

msmsajjadi/precision-recall-distributions official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
compute_prd in 5 papers prd_score.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · b9da61c36d3b8f11 · report fixture: signature eval_dist:ndarray/1/float, ref_dist:ndarray/1/float, num_angles:int/0/int, epsilon:float/0/float · returned tuple · level recorded 2026-09-22
compute_prd_from_embedding prd_score.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 5d84440e02c3a502 · report fixture: signature eval_data:ndarray/2/float, ref_data:ndarray/2/float, num_clusters:int/0/int, num_angles:int/0/int, num_runs:int/0/int, enforce_balance:bool/0/bool · returned tuple · level recorded 2026-09-22
prd_to_max_f_beta_pair prd_score.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 5adbefd0ebfa3e5e · report fixture: signature precision:ndarray/1/float, recall:ndarray/1/float, beta:int/0/int · returned tuple · level recorded 2026-09-22
ok1zjf/lbae community (archive-listed) 12 samples, 7 ran (1 instrument-failed) · 5 unverified
calculate_frechet_distance in 119 papers fid.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 5277c96076ea2fe5 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-22
corrupt datasets.py ran MIT (permissive) · 0bee687e2a3cbee8 · report fixture: signature x:Tensor/2/float, corrupt_method:str/0/str, corrupt_args:dict/0/? · returned Tensor · level recorded 2026-09-26
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket
sampler.py ran fingerprinted MIT (permissive) · 13d8e00ecc2023db · report fixture: signature a:ndarray/1/float · returned ndarray · level recorded 2026-09-26
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
image_utils.py ran fingerprinted MIT (permissive) · 8cdf564a25c20149 · report fixture: signature original:ndarray/3/int, reconstruction:ndarray/3/int · returned float64 · level recorded 2026-09-26
run_command in 61 papers sys_utils.py ran MIT (permissive) · 1bd4c31f00d84b70 · report fixture: signature command:str/0/str · returned str · level recorded 2026-09-26
todeg sampler.py ran MIT (permissive) · 0047ef4dfbce17cc · report fixture: signature x:ndarray/1/float · returned str · level recorded 2026-09-26
tohms sys_utils.py ran fingerprinted MIT (permissive) · c232fb314605487f · report fixture: signature s:int/0/int · returned str · level recorded 2026-09-26
calculate_activation_statistics in 75 papers fid.py unverified MIT (permissive) · 664d8c6c98c4ce7c · report
get_activations in 100 papers fid.py unverified MIT (permissive) · 579daa09f4887be8 · report
nearestPDX sampler.py unverified MIT (permissive) · 5a075ff84473359d · report
save_image in 18 papers image_utils.py unverified MIT (permissive) · afc8d137b43810a4 · report
ssim in 112 papers image_utils.py unverified MIT (permissive) · 239d3d651c2bea69 · report

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