Papers › FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

15 Nov 2021arXiv:2111.07677archive 2025-07-28

Jiawei Yu, Ye Zheng, Xiang Wang, Wei Li, Yushuang Wu, Rui Zhao, Liwei Wu

Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representation-based approaches extract normal image features with a deep convolutional neural network and characterize the corresponding distribution through non-parametric distribution estimation methods. The anomaly score is calculated by measuring the distance between the feature of the test image and the estimated distribution. However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies. To this end, we propose FastFlow implemented with 2D normalizing flows and use it as the probability distribution estimator. Our FastFlow can be used as a plug-in module with arbitrary deep feature extractors such as ResNet and vision transformer for unsupervised anomaly detection and localization. In training phase, FastFlow learns to transform the input visual feature into a tractable distribution and obtains the likelihood to recognize anomalies in inference phase. Extensive experimental results on the MVTec AD dataset show that FastFlow surpasses previous state-of-the-art methods in terms of accuracy and inference efficiency with various backbone networks. Our approach achieves 99.4% AUC in anomaly detection with high inference efficiency.

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 6 code samples harvested from 2 repositories linked to this paper: 5 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; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 6 samples from 2 repositories, 5 ran (5 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

RistoranteRist/FastFlow mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
gathierry/FastFlow mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MindSpore-paper-code-3/code10 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code7 mindsporeSyntology: not harvested report
openvinotoolkit/anomalib pytorchSyntology: 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

6 samples harvested: 5 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; 0 where Syntology's instrument failed) · 1 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.

5ran
1unverified

Licence: 0 of the 6 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.

RistoranteRist/FastFlow community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
calc_loss in 35 papers utils.py ran fingerprinted MIT (permissive) · a1c1c89b7d27cf53 · report fixture: signature z:Tensor/4/float, j:Tensor/4/float · returned tuple · level recorded 2026-09-24
get_score in 56 papers utils.py ran fingerprinted MIT (permissive) · 2f2d58311dd3969d · report fixture: signature z:Tensor/2/float, j:Tensor/2/float · returned Tensor · level recorded 2026-09-24
subnet_conv_1x1 model.py ran MIT (permissive) · bec083801249f9c0 · report fixture: signature c_in:int/0/int, c_out:int/0/int · returned Sequential · level recorded 2026-09-24
subnet_conv_3x3 model.py ran MIT (permissive) · 8c83518b50a675fa · report fixture: signature c_in:int/0/int, c_out:int/0/int · returned Sequential · level recorded 2026-09-24
load_image in 273 papers utils.py unverified MIT (permissive) · 9be60eff7630c2b3 · report
gathierry/FastFlow community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
subnet_conv_func fastflow.py ran Apache-2.0 (permissive) · 24b2b1978afd51b6 · report fixture: signature kernel_size:int/0/int, hidden_ratio:float/0/float · returned function · level recorded 2026-09-24

Tasks

Anomaly DetectionUnsupervised Anomaly DetectionWeakly Supervised Defect Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection MVTec AD Fastflow Detection AUROC 99.4 #36 of 148 Archive leaderboard report
Anomaly Detection MVTec AD Fastflow FPS 21.8 #36 of 148 Archive leaderboard report
Anomaly Detection MVTec AD Fastflow Segmentation AUROC 98.5 #36 of 148 Archive leaderboard report
Anomaly Detection MVTec LOCO AD FastFlow Avg. Detection AUROC 79.2 #28 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD FastFlow Detection AUROC (only logical) 75.5 #28 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD FastFlow Detection AUROC (only structural) 82.9 #28 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD FastFlow Segmentation AU-sPRO (until FPR 5%) 56.8 #28 of 40 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 FastFlow AUROC 66.7 #32 of 36 Archive leaderboard report
Anomaly Detection VisA FastFlow Segmentation AUPRO (until 30% FPR) 59.8 #48 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 ConvolutionAttentionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsGlobal Average PoolingKaiming InitializationLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionNormalizing FlowsReLUResidual BlockResidual ConnectionSoftmaxVision Transformer

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