Papers › EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies

EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies

25 Mar 2023arXiv:2303.14535archive 2025-07-28

Kilian Batzner, Lars Heckler, Rebecca König

Detecting anomalies in images is an important task, especially in real-time computer vision applications. In this work, we focus on computational efficiency and propose a lightweight feature extractor that processes an image in less than a millisecond on a modern GPU. We then use a student-teacher approach to detect anomalous features. We train a student network to predict the extracted features of normal, i.e., anomaly-free training images. The detection of anomalies at test time is enabled by the student failing to predict their features. We propose a training loss that hinders the student from imitating the teacher feature extractor beyond the normal images. It allows us to drastically reduce the computational cost of the student-teacher model, while improving the detection of anomalous features. We furthermore address the detection of challenging logical anomalies that involve invalid combinations of normal local features, for example, a wrong ordering of objects. We detect these anomalies by efficiently incorporating an autoencoder that analyzes images globally. We evaluate our method, called EfficientAD, on 32 datasets from three industrial anomaly detection dataset collections. EfficientAD sets new standards for both the detection and the localization of anomalies. At a latency of two milliseconds and a throughput of six hundred images per second, it enables a fast handling of anomalies. Together with its low error rate, this makes it an economical solution for real-world applications and a fruitful basis for future research.

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 35 code samples harvested from 8 repositories linked to this paper: 29 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 1 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 6 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): 35 samples from 8 repositories, 29 ran (29 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

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

openvinotoolkit/anomalib mentioned in paperpytorchApache-2.0Syntology: not harvested report
Eacient/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 9 ran (0 instrument-failed) · 0 unverified report
Emyyr/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
FourthM/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
LeapMind/PUAD mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MohammedEltoum/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
SimonThomine/DistillationAD mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Anomaly Detection via Reverse Distillation from One-Class Embedding (arXiv:2201.10703; that paper's own run record: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
VealFang/EfficientAD_realdata mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
WS-W/EfficientAD mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Zaza-97/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
arungansi/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
cinout/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
crimama/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
danielsoy/EfficientAD-1 mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dellysursh/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
guome/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
henry1985/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
lemonxiaohei/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
liutongkun/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
lorenzomammana/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
mjack3/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
nelson1425/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ntkhoa95/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
zhn6818/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ziyouzheilu/EfficientAD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
EighteenSprings/EfficientAD pytorchSyntology: not harvested report
alexriedel1/EfficientAD pytorchSyntology: not harvested report
arungansi/EfficientAD-1 pytorchSyntology: not harvested report
danielsoy/EfficientAD pytorchSyntology: not harvested report
furyhawk/EfficientAD pytorchSyntology: not harvested report
gellston/EfficientAD pytorchSyntology: not harvested report
rximg/EfficientAD pytorchSyntology: not harvested report
t22m003/EfficientAD 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.

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

35 samples harvested: 29 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 1 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 6 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
28ran
6unverified

Licence: 0 of the 35 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 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.

Eacient/EfficientAD community (archive-listed) 9 samples, 9 ran (0 instrument-failed) · 0 unverified
feature_normalization pretraining.py ran Apache-2.0 (permissive) · ded046c9ee356f89 · report fixture: signature extractor:callable/0/?, train_loader:list/1/tuple, steps:int/0/int · returned tuple · level recorded 2026-09-24
get_autoencoder common.py ran Apache-2.0 (permissive) · a2984f3ccda7db18 · report fixture: signature out_channels:int/0/int · returned Sequential · level recorded 2026-09-24
get_pdn benchmark.py ran Apache-2.0 (permissive) · 3c3ed7dd6e348895 · report fixture: signature out:int/0/int · returned Sequential · level recorded 2026-09-24
get_pdn_medium common.py ran Apache-2.0 (permissive) · f55436fae7d32859 · report fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24
get_pdn_small common.py ran Apache-2.0 (permissive) · cb104f86feb3ef61 · report fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24
predict in 126 papers efficientad.py ran Apache-2.0 (permissive) · 27ada34ea43ef9cb · report fixture: signature image:Tensor/4/float, teacher:callable/0/?, student:callable/0/?, autoencoder:callable/0/?, teacher_mean:Tensor/4/float, teacher_std:Tensor/4/float, q_st_start:Tensor/0/float, q_st_end:Tensor/0/float, q_ae_start:Tensor/0/float, q_ae_end:Tensor/0/float · returned tuple · level recorded 2026-09-24
test in 377 papers efficientad.py ran Apache-2.0 (permissive) · 21a6b1479ce8651c · report fixture: signature test_set:list/1/tuple, teacher:callable/0/?, student:callable/0/?, autoencoder:callable/0/?, teacher_mean:Tensor/4/float, teacher_std:Tensor/4/float, q_st_start:Tensor/0/float, q_st_end:Tensor/0/float, q_ae_start:Tensor/0/float, q_ae_end:Tensor/0/float, test_output_dir:NoneType/0/?, desc:str/0/str · returned float · level recorded 2026-09-25
train_transform in 7 papers efficientad.py ran Apache-2.0 (permissive) · 65449a6185e6dc7f · report fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24
train_transform in 7 papers pretraining.py ran Apache-2.0 (permissive) · 077ad902098508f5 · report fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24
LeapMind/PUAD community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
split_dataset in 65 papers puad/dataset.py ran Apache-2.0 (permissive) · 079e540378c4e38e · report fixture: signature img_dir:str/0/str, split_ratio:float/0/float, transform_1:callable/0/?, transform_2:callable/0/? · returned tuple · level recorded 2026-09-25
Zaza-97/EfficientAD community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
get_autoencoder common.py ran Apache-2.0 (permissive) · a3bf841cdd61584a · report fixture: signature im_height:int/0/int, im_width:int/0/int, out_height:int/0/int, out_width:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-24
get_autoencoder_small common.py ran Apache-2.0 (permissive) · 45760bcd8da72e6f · report fixture: signature im_height:int/0/int, im_width:int/0/int, out_height:int/0/int, out_width:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-24
get_pdn_small_max common.py ran Apache-2.0 (permissive) · 5820f47382ce8e2e · report fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24
train_transform in 7 papers efficientad.py ran Apache-2.0 (permissive) · a213bdb9746b0401 · report fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24
train_transform in 7 papers pretraining.py ran Apache-2.0 (permissive) · 08b41ec7d5727026 · report fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24
test in 377 papers efficientad.py unverified Apache-2.0 (permissive) · bde900c03717312f · report
cinout/EfficientAD community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
feature_normalization pretraining.py ran Apache-2.0 (permissive) · b0ac6b6a8e05c91a · report fixture: signature args:dict/0/?, extractor:callable/0/?, train_loader:list/1/tuple, steps:int/0/int · returned tuple · level recorded 2026-09-24
lid_mle efficientad.py ran Apache-2.0 (permissive) · f85e08a3d3105e5c · report fixture: signature data:Tensor/2/float, reference:Tensor/2/float, k:int/0/int, compute_mode:str/0/str · returned Tensor · level recorded 2026-09-24
make_layer in 76 papers common.py ran Apache-2.0 (permissive) · 144d898a5033505c · report fixture: signature block:callable/0/?, inplanes:int/0/int, planes:int/0/int, blocks:int/0/int, stride:int/0/int, norm_layer:callable/0/? · returned Sequential · level recorded 2026-09-24
normalizeData efficientad.py ran fingerprinted Apache-2.0 (permissive) · f1a2a9757a1d351a · report fixture: signature data:Tensor/2/float, minval:Tensor/0/float, maxval:Tensor/0/float · returned Tensor · level recorded 2026-09-24
stg2_transform efficientad_twosteps.py ran Apache-2.0 (permissive) · 1a23741c704a331b · report fixture: signature size:int/0/int · returned Compose · level recorded 2026-09-24
train_transform in 7 papers efficientad_twosteps.py ran Apache-2.0 (permissive) · b831876f274e1ec4 · report fixture: signature image:Image/0/?, config:dict/0/? · returned tuple · level recorded 2026-09-24
train_transform in 7 papers pretraining.py ran Apache-2.0 (permissive) · d1db9216b1ac0ae2 · report fixture: signature image:Image/0/?, size:int/0/int · returned tuple · level recorded 2026-09-24
lid_mle_modified efficientad.py unverified Apache-2.0 (permissive) · e5349e913e0cf837 · report
danielsoy/EfficientAD-1 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
test in 377 papers efficientaddrive.py ran Apache-2.0 (permissive) · fc52334326eef520 · report fixture: signature test_set:list/1/tuple, teacher:callable/0/?, student:callable/0/?, autoencoder:callable/0/?, teacher_mean:Tensor/4/float, teacher_std:Tensor/4/float, q_st_start:Tensor/0/float, q_st_end:Tensor/0/float, q_ae_start:Tensor/0/float, q_ae_end:Tensor/0/float, test_output_dir:NoneType/0/?, desc:str/0/str · returned float · level recorded 2026-09-24
dellysursh/EfficientAD community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_autoencoder common.py ran Apache-2.0 (permissive) · cf1eea789ca4d810 · report fixture: signature out_channels:int/0/int · returned Sequential · level recorded 2026-09-24
map_normalization efficientad.py unverified Apache-2.0 (permissive) · 23bcd10959f6f3db · report
henry1985/EfficientAD community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
compute_classification_roc mvtec_ad_evaluation/roc_curve_util.py ran Apache-2.0 (permissive) · 1171ab65a42cb909 · report fixture: signature anomaly_maps:list/1/ndarray, scoring_function:callable/0/?, ground_truth_labels:list/1/int · returned tuple · level recorded 2026-09-24
compute_pro in 9 papers mvtec_ad_evaluation/pro_curve_util.py ran Apache-2.0 (permissive) · 65ccd9c3a0376427 · report fixture: signature anomaly_maps:list/1/ndarray, ground_truth_maps:list/1/ndarray · returned tuple · level recorded 2026-09-24
generate_toy_dataset mvtec_ad_evaluation/generic_util.py ran Apache-2.0 (permissive) · 92626665be140960 · report fixture: signature num_images:int/0/int, image_width:int/0/int, image_height:int/0/int, gt_size:int/0/int · returned tuple · level recorded 2026-09-24
read_tiff mvtec_ad_evaluation/generic_util.py ran · honoured contract Apache-2.0 (permissive) · 4986e9bea3ab5f62 · report fixture: signature file_path_no_ext:str/0/str, exts:tuple/1/str · returned ndarray · level recorded 2026-09-24
trapezoid in 8 papers mvtec_ad_evaluation/generic_util.py ran fingerprinted Apache-2.0 (permissive) · 92db361050fcd08d · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, x_max:float/0/float · returned float64 · level recorded 2026-09-24
ntkhoa95/EfficientAD community (archive-listed) 3 samples, 0 ran · 3 unverified
inference in 65 papers inference.py unverified Apache-2.0 (permissive) · 8766003511e1dc5c · report
inference_onnx inference.py unverified Apache-2.0 (permissive) · dfe0b32f2056683b · report
load_model in 479 papers inference.py unverified Apache-2.0 (permissive) · a849040c6073d454 · report

Tasks

Anomaly DetectionComputational EfficiencySemi-supervised Anomaly DetectionUnsupervised Anomaly Detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection MVTec AD EfficientAD (early stopping) Detection AUROC 99.8 #7 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD (early stopping) FPS 269 #7 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-M Detection AUROC 99.1 #45 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-M FPS 269 #45 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-M Segmentation AUPRO 93.5 #45 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-S Detection AUROC 98.7 #51 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-S FPS 614 #51 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-S Segmentation AP 65.9 #51 of 148 Archive leaderboard report
Anomaly Detection MVTec AD EfficientAD-S Segmentation AUPRO 93.1 #51 of 148 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-M Avg. Detection AUROC 90.7 #6 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-M Detection AUROC (only logical) 86.8 #6 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-M Detection AUROC (only structural) 94.7 #6 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-M Segmentation AU-sPRO (until FPR 5%) 79.8 #6 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-S Avg. Detection AUROC 90.0 #10 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-S Detection AUROC (only logical) 85.8 #10 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-S Detection AUROC (only structural) 94.1 #10 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD EfficientAD-S Segmentation AU-sPRO (until FPR 5%) 77.8 #10 of 40 Archive leaderboard report
Anomaly Detection VisA EfficientAD-M Detection AUROC 98.1 #10 of 50 Archive leaderboard report
Anomaly Detection VisA EfficientAD-M Segmentation AUPRO (until 30% FPR) 94.0 #10 of 50 Archive leaderboard report
Anomaly Detection VisA EfficientAD-S Detection AUROC 97.5 #15 of 50 Archive leaderboard report
Anomaly Detection VisA EfficientAD-S Segmentation AUPRO (until 30% FPR) 93.1 #15 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.

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