Papers › RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

9 Mar 2024CVPR 2024 1arXiv:2403.05897archive 2025-07-28

Ximiao Zhang, Min Xu, Xiuzhuang Zhou

Self-supervised feature reconstruction methods have shown promising advances in industrial image anomaly detection and localization. Despite this progress, these methods still face challenges in synthesizing realistic and diverse anomaly samples, as well as addressing the feature redundancy and pre-training bias of pre-trained feature. In this work, we introduce RealNet, a feature reconstruction network with realistic synthetic anomaly and adaptive feature selection. It is incorporated with three key innovations: First, we propose Strength-controllable Diffusion Anomaly Synthesis (SDAS), a diffusion process-based synthesis strategy capable of generating samples with varying anomaly strengths that mimic the distribution of real anomalous samples. Second, we develop Anomaly-aware Features Selection (AFS), a method for selecting representative and discriminative pre-trained feature subsets to improve anomaly detection performance while controlling computational costs. Third, we introduce Reconstruction Residuals Selection (RRS), a strategy that adaptively selects discriminative residuals for comprehensive identification of anomalous regions across multiple levels of granularity. We assess RealNet on four benchmark datasets, and our results demonstrate significant improvements in both Image AUROC and Pixel AUROC compared to the current state-o-the-art methods. The code, data, and models are available at https://github.com/cnulab/RealNet.

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 10 code samples harvested from 1 repository linked to this paper: 10 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; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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.

cnulab/realnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 10 ran (2 instrument-failed) · 0 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

10 samples harvested: 10 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; 2 where Syntology's instrument failed) · 0 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.

2ran · our draft was wrong
8ran

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 cnulab/realnet. “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.

cnulab/realnet official repository 10 samples, 10 ran (2 instrument-failed) · 0 unverified
SDAS_sample train_diffusion.py ran MIT (permissive) · c46ea6fc2bd50337 · report fixture: signature imgs:Tensor/4/float, class_labels:Tensor/1/int, model:callable/0/?, sampler:DummySampler/0/? · returned tuple · level recorded 2026-09-24
build_image_reader datasets/image_reader.py ran · our draft was wrong MIT (permissive) · 02edfca0848f4ad3 · report fixture: signature cfg_reader:dict/0/? · returned OpenCVReader · level recorded 2026-09-24
compute_top_k in 7 papers train_classifier.py ran MIT (permissive) · f85c45c8d1765da4 · report fixture: signature logits:Tensor/2/float, labels:Tensor/1/int, k:int/0/int, reduction:str/0/str · returned float · level recorded 2026-09-24
lerp_np in 9 papers datasets/realnet_dataset.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
rand_perlin_2d_np datasets/realnet_dataset.py ran MIT (permissive) · 4bb5faf95cfc1665 · report fixture: signature shape:tuple/1/int, res:tuple/1/int, fade:callable/0/? · returned ndarray · level recorded 2026-09-24
random_between_a_and_b sample.py ran fingerprinted MIT (permissive) · 38a9840dccf671bd · report fixture: signature a:float/0/float, b:float/0/float · returned float · level recorded 2026-09-24
update_config in 54 papers train_realnet.py ran MIT (permissive) · 3e33555f9dc00ec5 · report fixture: signature config:Config/0/?, args:Args/0/? · returned Config · level recorded 2026-09-24
update_config in 54 papers sample.py ran · our draft was wrong MIT (permissive) · 4102f1fdf8eafea4 · report fixture: signature config:Config/0/?, world_size:int/0/int · returned Config · level recorded 2026-09-24
update_config in 54 papers train_classifier.py ran MIT (permissive) · 0402f903a58abc8a · report fixture: signature config:Config/0/?, args:Args/0/? · returned Config · level recorded 2026-09-24
update_config in 54 papers train_diffusion.py ran MIT (permissive) · 39f7b5d3324b349c · report fixture: signature config:Config/0/?, args:Args/0/? · returned Config · level recorded 2026-09-24

Tasks

Anomaly Detectionfeature selection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection BTAD RealNet Detection AUROC 96.1 #3 of 15 Archive leaderboard report
Anomaly Detection BTAD RealNet Segmentation AUROC 97.9 #3 of 15 Archive leaderboard report
Anomaly Detection MPDD RealNet Detection AUROC 96.3 #8 of 16 Archive leaderboard report
Anomaly Detection MPDD RealNet Segmentation AUROC 98.2 #8 of 16 Archive leaderboard report
Anomaly Detection MVTec AD RealNet Detection AUROC 99.6 #21 of 148 Archive leaderboard report
Anomaly Detection MVTec AD RealNet Segmentation AUPRO 93.0 #21 of 148 Archive leaderboard report
Anomaly Detection MVTec AD RealNet Segmentation AUROC 99.0 #21 of 148 Archive leaderboard report
Anomaly Detection VisA RealNet Detection AUROC 97.8 #12 of 50 Archive leaderboard report
Anomaly Detection VisA RealNet Segmentation AUROC 98.8 #12 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

Diffusion

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