Papers › Towards Total Recall in Industrial Anomaly Detection

Towards Total Recall in Industrial Anomaly Detection

15 Jun 2021CVPR 2022 1arXiv:2106.08265archive 2025-07-28

Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose PatchCore, which uses a maximally representative memory bank of nominal patch-features. PatchCore offers competitive inference times while achieving state-of-the-art performance for both detection and localization. On the challenging, widely used MVTec AD benchmark PatchCore achieves an image-level anomaly detection AUROC score of up to 99.6%, more than halving the error compared to the next best competitor. We further report competitive results on two additional datasets and also find competitive results in the few samples regime.\freefootnote{^* Work done during a research internship at Amazon AWS.} Code: github.com/amazon-research/patchcore-inspection.

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 36 code samples harvested from 8 repositories linked to this paper: 28 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 31 samples from 7 repositories, 24 ran (21 with no instrument failure; 3 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.

No sample is linked to this paper from 3 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. 3 of the 28 samples that ran have no recorded date.

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

amazon-research/patchcore-inspection officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
JoegameZhou/PatchCore mentioned on GitHubmindsporeApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
OpenAOI/anodet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization (arXiv:2011.08785; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Ultranity/Anomaly.Paddle mentioned on GitHubpaddleApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
amazon-science/patchcore-inspection mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
any-tech/PatchCore-ex mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
captainfffsama/pathcore mentioned on GitHubpytorchSyntology: not harvested report
hcw-00/PatchCore_anomaly_detection mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
tbcvContributor/DeepHawkeye mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 4 ran (2 instrument-failed) · 3 unverified report
tiskw/patchcore-ad mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
totoroKalic/patchcore-mindspore mentioned on GitHubmindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-4 mindsporeSyntology: not harvested report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
openvinotoolkit/anomalib pytorchApache-2.0Syntology: not harvested report
rvorias/ind_knn_ad pytorchMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
taikiinoue45/PatchCore pytorchMITSyntology: not harvested report
yangyucheng000/patchcore mindsporeSyntology: 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.

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

36 samples harvested: 28 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 8 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.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
23ran
8unverified

Licence: 4 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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. “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.

amazon-research/patchcore-inspection official repository 5 samples, 4 ran (0 instrument-failed) · 1 unverified
compute_and_store_final_results src/patchcore/utils.py ran Apache-2.0 (permissive) · e80ac3c0c9f85f59 · report fixture: signature results_path:str/0/str, results:list/1/list, row_names:list/1/str, column_names:list/1/str · returned dict · level recorded 2026-09-26
compute_imagewise_retrieval_metrics src/patchcore/metrics.py ran Apache-2.0 (permissive) · 9a6ba99206d2a918 · report fixture: signature anomaly_prediction_weights:ndarray/1/float, anomaly_ground_truth_labels:ndarray/1/int · returned dict · level recorded 2026-09-25
compute_pixelwise_retrieval_metrics src/patchcore/metrics.py ran Apache-2.0 (permissive) · 45cfbfc30f32be75 · report fixture: signature anomaly_segmentations:ndarray/3/float, ground_truth_masks:ndarray/3/int · returned dict · level recorded 2026-09-25
create_storage_folder src/patchcore/utils.py ran Apache-2.0 (permissive) · 4847c26291a5d907 · report fixture: signature main_folder_path:str/0/str, project_folder:str/0/str, group_folder:str/0/str, mode:str/0/str · returned str · level recorded 2026-09-25
dataset in 10 papers bin/load_and_evaluate_patchcore.py unverified Apache-2.0 (permissive) · 1850ff44d813323e · report
JoegameZhou/PatchCore community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
createDatasetJson src/dataset.py ran Apache-2.0 (permissive) · b8c46d57235fa543 · report fixture: signature dataset_path:str/0/str, category:str/0/str, data_transforms:callable/0/?, gt_transforms:callable/0/? · returned tuple · level recorded 2026-09-24
embedding_concat src/operator.py ran Apache-2.0 (permissive) · 40df71d26759ce01 · report fixture: signature x:ndarray/4/float, y:ndarray/4/float · returned ndarray · level recorded 2026-09-24
fold in 10 papers src/operator.py ran Apache-2.0 (permissive) · b4bfdc071e0f7908 · report fixture: signature col:ndarray/6/float, input_shape:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int · returned ndarray · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
postprocess.py ran Apache-2.0 (permissive) · c3cae68ec9e6850c · report fixture: signature input_:ndarray/3/float, mean_:list/1/float, std_:list/1/float · returned ndarray · level recorded 2026-09-24
replace_self src/pthtockpt.py ran fingerprinted Apache-2.0 (permissive) · ddeed4d4fc8e73b2 · report fixture: signature name1:str/0/str, str1:str/0/str, str2:str/0/str · returned str · level recorded 2026-09-24
unfold in 7 papers src/operator.py ran Apache-2.0 (permissive) · 75cfa7e86dd91ed0 · report fixture: signature img:ndarray/4/float, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned ndarray · level recorded 2026-09-24
Ultranity/Anomaly.Paddle community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
johnson_lindenstrauss_min_dim dim_reduction/random_projection.py ran Apache-2.0 (permissive) · 0a43d57bcdbc3765 · report fixture: signature n_samples:int/0/int, eps:float/0/float · returned int64 · level recorded 2026-09-24
rescale in 30 papers utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f51e6ad9c7104a5a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
str2bool in 533 papers infer.py ran · violated contract Apache-2.0 (permissive) · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
amazon-science/patchcore-inspection community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
set_torch_device src/patchcore/utils.py ran · our draft was wrong Apache-2.0 (permissive) · 61fd3c8459a48853 · report fixture: signature gpu_ids:list/1/empty · returned device · level recorded 2026-09-24
load in 392 papers src/patchcore/backbones.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · b426324b6ed6ccaf · report
any-tech/PatchCore-ex community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
assemble_patch utils/visualize.py ran Apache-2.0 (permissive) · 02bea3555bf26ceb · report fixture: signature idx_patch:list/1/int, imgs_coreset:ndarray/4/int, HW_map:list/1/int · returned ndarray · level recorded 2026-09-24
calc_imagewise_metrics utils/metrics.py ran Apache-2.0 (permissive) · d64d475597e3e18e · report fixture: signature D:dict/0/?, type_normal:str/0/str · returned tuple · level recorded 2026-09-24
calc_pixelwise_metrics utils/metrics.py ran Apache-2.0 (permissive) · e6b66178d86edc78 · report fixture: signature D:dict/0/?, y:dict/0/? · returned tuple · level recorded 2026-09-24
overlay_heatmap_on_image utils/visualize.py ran Apache-2.0 (permissive) · 591e30226a9f25b0 · report fixture: signature img:ndarray/3/int, heatmap:ndarray/2/float, ratio_img:float/0/float · returned ndarray · level recorded 2026-09-24
tbcvContributor/DeepHawkeye community (archive-listed) 7 samples, 4 ran (2 instrument-failed) · 3 unverified
conv1x1 in 691 papers src/wide_res_model.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 2a80220dabcb742a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers src/wide_res_model.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 600ff2c45e0de056 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
cvt2heatmap src/utils.py ran fingerprinted Apache-2.0 (permissive) · cd61b6846e7dd644 · report fixture: signature gray:ndarray/2/float · returned ndarray · level recorded 2026-09-24
min_max_norm in 19 papers
census: 3 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/utils.py ran fingerprinted Apache-2.0 (permissive) · 373674457d45997f · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-24
heatmap_on_image src/utils.py unverified Apache-2.0 (permissive) · 899548de5f36cc3c · report
trt_wide_resnet50_2 trt_tools/trt_wide_res_model.py unverified Apache-2.0 (permissive) · 348384a804271606 · report
wide_resnet50_2 src/wide_res_model.py unverified Apache-2.0 (permissive) · bbc9958e58a3a24b · report
tiskw/patchcore-ad community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
auto_threshold patchcore/utils.py ran fingerprinted MIT (permissive) · 31bb4bbf1cab798a · report fixture: signature scores_good:list/1/float, coef_sigma:float/0/float · returned tuple · level recorded 2026-09-24
main_summarize main_mvtecad.py unverified MIT (permissive) · 1e3b3c661fef6c1a · report
rvorias/ind_knn_ad community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
create_dataset in 47 papers indad/workspace.py ran MIT (permissive) · 774c2acb59a77761 · report fixture: signature parent:str/0/str, name:str/0/str · returned PosixPath · level recorded 2026-09-24
import_images indad/workspace.py ran MIT (permissive) · 20c1c0be389a566e · report fixture: signature root:PosixPath/0/?, files:list/1/tuple, split:str/0/str, label:str/0/str · returned list · level recorded 2026-09-24
inspect_dataset indad/workspace.py ran MIT (permissive) · b21c2ea9ce7a27e6 · report fixture: signature root:PosixPath/0/? · returned dict · level recorded 2026-09-24
list_changes indad/curation.py ran MIT (permissive) · f72e12b0cce93f61 · report fixture: signature root:PosixPath/0/? · returned list · level recorded 2026-09-24
serialize_results indad/utils.py ran MIT (permissive) · af18bba97264c730 · report fixture: signature results:dict/0/? · returned str · level recorded 2026-09-24
get_coreset_idx_randomp indad/utils.py unverified MIT (permissive) · 69f7e0b8a9ede02e · report
run_onnx indad/utils.py unverified MIT (permissive) · 095a5a07515ea7a9 · report

Tasks

3D Anomaly DetectionAnomaly ClassificationAnomaly DetectionAnomaly SegmentationOutlier DetectionUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Anomaly Detection Anomaly-ShapeNet10 PatchCore (FPFH) O-AUROC 0.884 #2 of 7 Archive leaderboard report
3D Anomaly Detection Anomaly-ShapeNet10 PatchCore (FPFH) P-AUROC 0.923 #2 of 7 Archive leaderboard report
3D Anomaly Detection Anomaly-ShapeNet10 PatchCore (PointMAE) O-AUROC 0.574 #5 of 7 Archive leaderboard report
3D Anomaly Detection Anomaly-ShapeNet10 PatchCore (PointMAE) P-AUROC 0.645 #5 of 7 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH+Raw) Mean Performance of P. and O. 0.687 #12 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH+Raw) Object AUROC 0.682 #12 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH+Raw) Point AUROC 0.692 #12 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (PointMAE) Mean Performance of P. and O. 0.614 #15 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (PointMAE) Object AUROC 0.594 #15 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (PointMAE) Point AUROC 0.634 #15 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH) Mean Performance of P. and O. 0.5925 #17 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH) Object AUROC 0.593 #17 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PatchCore (FPFH) Point AUROC 0.592 #17 of 19 Archive leaderboard report
Anomaly Classification GoodsAD PatchCore-100% AUPR 86.1 #1 of 11 Archive leaderboard report
Anomaly Classification GoodsAD PatchCore-100% AUROC 85.5 #1 of 11 Archive leaderboard report
Anomaly Classification GoodsAD PatchCore-1% AUPR 83.3 #2 of 11 Archive leaderboard report
Anomaly Classification GoodsAD PatchCore-1% AUROC 81.4 #2 of 11 Archive leaderboard report
Anomaly Detection AeBAD-S PatchCore Detection AUROC 71.0 #4 of 8 Archive leaderboard report
Anomaly Detection AeBAD-S PatchCore Segmentation AUPRO 87.8 #4 of 8 Archive leaderboard report
Anomaly Detection AeBAD-V PatchCore Detection AUROC 70.7 #3 of 7 Archive leaderboard report
Anomaly Detection MPDD PatchCore Detection AUROC 82.12 #14 of 16 Archive leaderboard report
Anomaly Detection MPDD PatchCore Segmentation AUROC 95.66 #14 of 16 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Large Detection AUROC 99.6 #20 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Large FPS 5.88 #20 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Large Segmentation AUPRO 93.5 #20 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Large Segmentation AUROC 98.2 #20 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Detection AUROC 99.2 #43 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore Segmentation AUROC 98.4 #43 of 148 Archive leaderboard report
Anomaly Detection MVTec AD PatchCore(16shot) Detection AUROC 95.4 #89 of 148 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Avg. Detection AUROC 80.3 #26 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Detection AUROC (only logical) 75.8 #26 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Segmentation AU-sPRO (until FPR 5%) 39.7 #26 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Ensemble Avg. Detection AUROC 79.4 #27 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Ensemble Detection AUROC (only logical) 71.0 #27 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Ensemble Detection AUROC (only structural) 87.7 #27 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PatchCore Ensemble Segmentation AU-sPRO (until FPR 5%) 36.5 #27 of 40 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

Coresets

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