Papers › PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization

PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization

17 Nov 2020arXiv:2011.08785archive 2025-07-28

Thomas Defard, Aleksandr Setkov, Angelique Loesch, Romaric Audigier

We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting. PaDiM makes use of a pretrained convolutional neural network (CNN) for patch embedding, and of multivariate Gaussian distributions to get a probabilistic representation of the normal class. It also exploits correlations between the different semantic levels of CNN to better localize anomalies. PaDiM outperforms current state-of-the-art approaches for both anomaly detection and localization on the MVTec AD and STC datasets. To match real-world visual industrial inspection, we extend the evaluation protocol to assess performance of anomaly localization algorithms on non-aligned dataset. The state-of-the-art performance and low complexity of PaDiM make it a good candidate for many industrial applications.

PaperPDFCodeCode 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="2011.08785")

Code

Syntology Ran 7 of 7 code samples harvested from 4 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 6 samples from 4 repositories, 6 ran; 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.

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

CuberrChen/PaDiM-Paddle mentioned on GitHubpaddle report
Jaizxzx/PaDiM mentioned on GitHubpytorch report
JohnnyHopp/PaDiM-EfficientNetV2 mentioned on GitHubpytorch report
Jonas1302/anomalib mentioned on GitHubjax report
OpenAOI/anodet mentioned on GitHubpytorch report
Pangoraw/PaDiM mentioned on GitHubpytorch report
Ultranity/Anomaly.Paddle mentioned on GitHubpaddleApache-2.0 report
ingbeeedd/PaDiM-EfficientNet mentioned on GitHubpytorch report
koheitokda/PaDiM mentioned on GitHubpytorch report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0 report
openvinotoolkit/anomalib mentioned on GitHubpytorchApache-2.0 report
pranavjadhav001/tf_padim mentioned on GitHubtf report
remmarp/PaDiM-TF mentioned on GitHubtf report
taikiinoue45/PaDiM mentioned on GitHubpytorch 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

7 samples harvested; 7 ran; 1 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.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
1ran · fixture could not drive it

Licence: 3 of the 7 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 4 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

denormalization koheitokda/PaDiM/original_data.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · e6842b1e038b1c52 · report
embedding_concat koheitokda/PaDiM/original_data.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 95dff3e95b0216e4 · report
fused_map FlappyPeggy/Registration-based-PaDiM/regpadim/e2eutils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 62c0eeb67a3daaa8 · report
get_indices OpenAOI/anodet/anodet/padim.py community (archive-listed) ran · honoured contract MIT (permissive) · 1c2fbdd38f225973 · report
get_radius Pangoraw/PaDiM/padim/padim_svdd.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · def857abe2885673 · report
gkern FlappyPeggy/Registration-based-PaDiM/regpadim/e2eutils.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 216ef2c2ea151173 · report
str2bool identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 7c508037b40522af · report

Tasks

Anomaly DetectionAnomaly LocalizationUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Hyper-Kvasir Dataset PaDiM AUC 0.923 #4 of 6 Archive leaderboard report
Anomaly Detection LAG PaDiM AUC 0.688 #5 of 5 Archive leaderboard report
Anomaly Detection MVTec AD PaDiM Detection AUROC 97.9 #70 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PaDiM-WR50-Rd550 Detection AUROC 95.3 #90 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PaDiM-WR50-Rd550 FPS 4.4 #90 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PaDiM-WR50-Rd550 Segmentation AUROC 97.5 #90 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PaDiM-R18-Rd100 Segmentation AUROC 96.7 #136 of 148 Archive leaderboard report
Anomaly Detection VisA PaDiM Segmentation AUPRO (until 30% FPR) 85.9 #43 of 50 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetGlobal Average PoolingInverted Residual BlockKaiming InitializationMax PoolingPointwise ConvolutionRMSPropReLUResidual BlockResidual ConnectionSigmoid ActivationSqueeze-and-Excitation BlockWide Residual BlockWideResNet

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