Papers › EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
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.
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):
get_harvested_code_for_paper(arxiv_id="2303.14535")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2303.14535", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2303.14535")
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:
- SimonThomine/DistillationAD, community (archive-listed): harvested for another paper, listed under the repository
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.
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.
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.
ded046c9ee356f89 · report
fixture: signature extractor:callable/0/?, train_loader:list/1/tuple, steps:int/0/int · returned tuple · level recorded 2026-09-24 a2984f3ccda7db18 · report
fixture: signature out_channels:int/0/int · returned Sequential · level recorded 2026-09-24 3c3ed7dd6e348895 · report
fixture: signature out:int/0/int · returned Sequential · level recorded 2026-09-24 f55436fae7d32859 · report
fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24 cb104f86feb3ef61 · report
fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24 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 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 65449a6185e6dc7f · report
fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24 077ad902098508f5 · report
fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24 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 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 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 5820f47382ce8e2e · report
fixture: signature out_channels:int/0/int, padding:bool/0/bool · returned Sequential · level recorded 2026-09-24 a213bdb9746b0401 · report
fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24 08b41ec7d5727026 · report
fixture: signature image:Image/0/? · returned tuple · level recorded 2026-09-24 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 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 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 f1a2a9757a1d351a · report
fixture: signature data:Tensor/2/float, minval:Tensor/0/float, maxval:Tensor/0/float · returned Tensor · level recorded 2026-09-24 1a23741c704a331b · report
fixture: signature size:int/0/int · returned Compose · level recorded 2026-09-24 b831876f274e1ec4 · report
fixture: signature image:Image/0/?, config:dict/0/? · returned tuple · level recorded 2026-09-24 d1db9216b1ac0ae2 · report
fixture: signature image:Image/0/?, size:int/0/int · returned tuple · level recorded 2026-09-24 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 cf1eea789ca4d810 · report
fixture: signature out_channels:int/0/int · returned Sequential · level recorded 2026-09-24 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 65ccd9c3a0376427 · report
fixture: signature anomaly_maps:list/1/ndarray, ground_truth_maps:list/1/ndarray · returned tuple · level recorded 2026-09-24 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 4986e9bea3ab5f62 · report
fixture: signature file_path_no_ext:str/0/str, exts:tuple/1/str · returned ndarray · level recorded 2026-09-24 92db361050fcd08d · report
fixture: signature x:ndarray/1/float, y:ndarray/1/float, x_max:float/0/float · returned float64 · level recorded 2026-09-24 a849040c6073d454 · report
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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