Papers › Target before Shooting: Accurate Anomaly Detection and Localization under One...

Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval

13 Aug 2023arXiv:2308.06748archive 2025-07-28

Hanxi Li, Jianfei Hu, Bo Li, Hao Chen, Yongbin Zheng, Chunhua Shen

In this work, by re-examining the "matching" nature of Anomaly Detection (AD), we propose a new AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those "global nearest neighbors", by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its "local nearest neighbor" and the "non-background" probability. The proposed method is termed "Cascade Patch Retrieval" (CPR) in this work. Different from the conventional patch-matching-based AD algorithms, CPR selects proper "targets" (reference images and locations) before "shooting" (patch-matching). On the well-acknowledged MVTec AD, BTAD and MVTec-3D AD datasets, the proposed algorithm consistently outperforms all the comparing SOTA methods by remarkable margins, measured by various AD metrics. Furthermore, CPR is extremely efficient. It runs at the speed of 113 FPS with the standard setting while its simplified version only requires less than 1 ms to process an image at the cost of a trivial accuracy drop. The code of CPR is available at https://github.com/flyinghu123/CPR.

PaperPDFCodeCode 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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (8 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

flyinghu123/cpr officialmentioned in paperpytorchMITSyntology: 11 samples, 9 ran (1 instrument-failed) · 2 unverified 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 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 · our draft was wrong
8ran
2unverified

Licence: 3 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 flyinghu123/cpr. “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.

flyinghu123/cpr official repository 11 samples, 9 ran (1 instrument-failed) · 2 unverified
compute_image_auc metrics.py ran fingerprinted MIT (permissive) · 9904f18fa913eb37 · report fixture: signature gts:ndarray/1/int, preds:ndarray/1/float · returned float · level recorded 2026-09-24
entropy_pytorch models/grb.py ran fingerprinted MIT (permissive) · afd1fd4c67e83001 · report fixture: signature pk:Tensor/2/float, qk:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
fix_seeds utils.py ran MIT (permissive) · 0c3e0e613af57ee1 · report fixture: signature seed:int/0/int, with_torch:bool/0/bool, with_cuda:bool/0/bool · returned function · level recorded 2026-09-24
generate_fractal_noise_2d in 6 papers libs/perlin.py ran MIT (permissive) here; the stored copy is pointer only · 293a2b1189b747fd · report fixture: signature shape:tuple/1/int, res:tuple/1/int, octaves:int/0/int, persistence:float/0/float · returned ndarray · level recorded 2026-09-25
generate_perlin_noise_2d in 7 papers libs/perlin.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ed9e127befc02046 · report fixture: signature shape:tuple/1/int, res:tuple/1/int · returned ndarray · level recorded 2026-09-25
get_grb models/grb.py ran MIT (permissive) · c05bbe23123f3bf7 · report fixture: signature train_features:Tensor/4/float · returned GlobalRetrievalBranch · level recorded 2026-09-24
lerp_np in 9 papers libs/perlin.py ran MIT (permissive) here; the stored copy is pointer only · 4de91a4627a51ea2 · report fixture: signature x:ndarray/2/float, y:ndarray/2/float, w:ndarray/2/float · returned ndarray · level recorded 2026-09-25
pixel_params_verify metrics.py ran fingerprinted MIT (permissive) · fc87506f23fa4651 · report fixture: signature gts:ndarray/3/float, preds:ndarray/3/float · returned tuple · level recorded 2026-09-24
save_dependencies_files utils.py ran MIT (permissive) · 3eec1fa82531e363 · report fixture: signature root_path:str/0/str · returned list · level recorded 2026-09-24
compute_image_auc_torch metrics.py unverified MIT (permissive) · aa3eaa45e0fc06c6 · report
get_feb models/feb.py unverified MIT (permissive) · c0449268a49c4f3d · report

Tasks

Anomaly DetectionSupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection BTAD CPR Detection AUROC 94.8 #9 of 15 Archive leaderboard report
Anomaly Detection BTAD CPR Segmentation AP 70.3 #9 of 15 Archive leaderboard report
Anomaly Detection BTAD CPR Segmentation AUPRO 85.1 #9 of 15 Archive leaderboard report
Anomaly Detection BTAD CPR Segmentation AUROC 98.4 #9 of 15 Archive leaderboard report
Anomaly Detection MVTec 3D-AD (RGB) CPR Detection AUROC 88.5 #2 of 2 Archive leaderboard report
Anomaly Detection MVTec 3D-AD (RGB) CPR Segmentation AP 57.8 #2 of 2 Archive leaderboard report
Anomaly Detection MVTec 3D-AD (RGB) CPR Segmentation AUPRO 96.9 #2 of 2 Archive leaderboard report
Anomaly Detection MVTec 3D-AD (RGB) CPR Segmentation AUROC 99.1 #2 of 2 Archive leaderboard report
Anomaly Detection MVTec AD CPR Detection AUROC 99.7 #12 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR FPS 113 #12 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR Segmentation AP 82.7 #12 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR Segmentation AUPRO 97.8 #12 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR Segmentation AUROC 99.2 #12 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast Detection AUROC 99.7 #13 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast FPS 245 #13 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast Segmentation AP 82.3 #13 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast Segmentation AUPRO 97.7 #13 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast Segmentation AUROC 99.2 #13 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster Detection AUROC 99.4 #34 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster FPS 478 #34 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster Segmentation AP 80.6 #34 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster Segmentation AUPRO 97.3 #34 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster Segmentation AUROC 99.0 #34 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-faster(TensorRT) FPS 1016 #146 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR-fast(TensorRT) FPS 362 #147 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CPR(TensorRT) FPS 130 #148 of 148 Archive leaderboard report
Supervised Anomaly Detection BTAD CPR Detection AUROC 98.3 #1 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD CPR Segmentation AP 84.0 #1 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD CPR Segmentation AUPRO 91.4 #1 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD CPR Segmentation AUROC 99.1 #1 of 2 Archive leaderboard report
Supervised Anomaly Detection MVTec AD CPR Detection AUROC 99.7 #2 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD CPR Segmentation AP 86.0 #2 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD CPR Segmentation AUPRO 98.3 #2 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD CPR Segmentation AUROC 99.6 #2 of 8 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 ConvolutionAuxiliary ClassifierAverage PoolingBatch NormalizationContrastive LearningConvolutionDense ConnectionsDropoutGlobal Average PoolingInception ModuleInception v2Kaiming InitializationLDAMax PoolingReLUResidual ConnectionSoftmaxWide 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