Papers › Anomaly Detection via Reverse Distillation from One-Class Embedding

Anomaly Detection via Reverse Distillation from One-Class Embedding

26 Jan 2022CVPR 2022 1arXiv:2201.10703archive 2025-07-28

Hanqiu Deng, Xingyu Li

Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD).The representation discrepancy of anomalies in the teacher-student (T-S) model provides essential evidence for AD. However, using similar or identical architectures to build the teacher and student models in previous studies hinders the diversity of anomalous representations. To tackle this problem, we propose a novel T-S model consisting of a teacher encoder and a student decoder and introduce a simple yet effective "reverse distillation" paradigm accordingly. Instead of receiving raw images directly, the student network takes teacher model's one-class embedding as input and targets to restore the teacher's multiscale representations. Inherently, knowledge distillation in this study starts from abstract, high-level presentations to low-level features. In addition, we introduce a trainable one-class bottleneck embedding (OCBE) module in our T-S model. The obtained compact embedding effectively preserves essential information on normal patterns, but abandons anomaly perturbations. Extensive experimentation on AD and one-class novelty detection benchmarks shows that our method surpasses SOTA performance, demonstrating our proposed approach's effectiveness and generalizability.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 18 code samples: 16 from 4 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 18: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 3 repositories, 10 ran (8 with no instrument failure; 2 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 14 samples that ran have no recorded date.

hq-deng/RD4AD officialpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
SimonThomine/DistillationAD mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
SimonThomine/RememberingNormality mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Merenguelkl/Reverse_Disstilation pytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified 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

18 samples harvested: 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. “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.

4ran · our draft was wrong
10ran
4unverified

Licence: 15 of the 18 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 4 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. 2 samples are listed last, in a group without a repository. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hq-deng/RD4AD official repository 3 samples, 2 ran (0 instrument-failed) · 1 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
de_resnet.py ran fingerprinted MIT (permissive) · ce529f9eb01d326b · report fixture: returned BasicBlock · level recorded 2026-09-22
Bottleneck in 98 papers de_resnet.py ran MIT (permissive) · 2d33e6c48f4a2845 · report fixture: returned Bottleneck · level recorded 2026-09-22
ResNet in 139 papers de_resnet.py unverified MIT (permissive) · 6f9abfc5f148cc04 · report
SimonThomine/DistillationAD community (archive-listed) 5 samples, 4 ran (2 instrument-failed) · 1 unverified
deBasicBlock models/ReverseDistillation/de_resnet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3f0806f63aee3bdd · report fixture: returned deBasicBlock · level recorded 2026-09-22
deResNet models/ReverseDistillation/de_resnet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 274a066ad1685214 · report fixture: returned deResNet · level recorded 2026-09-22
deconv2x2 in 5 papers models/ReverseDistillation/de_resnet.py ran · our draft was wrong no licence file found · pointer only · 8d035278d5e4a82a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
init_weights in 109 papers models/ReverseDistillation/de_resnet.py ran · our draft was wrong no licence file found · pointer only · 5c6ddf757751d73a · report fixture: signature instance:callable/0/? · returned SmallModel · level recorded 2026-09-22
deBottleneck models/ReverseDistillation/de_resnet.py unverified no licence file found · pointer only · 1e173e8f7793f155 · report
SimonThomine/RememberingNormality community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
memoryModule models/RD/de_resnetRM.py ran fingerprinted no licence file found · pointer only · ddda7402c136e2b4 · report fixture: signature x:Tensor/4/float, normality:bool/0/bool · returned Tensor · level recorded 2026-09-24
ResNet in 139 papers models/RD/de_resnetRM.py unverified no licence file found · pointer only · c27cbb6fba18f4ba · report
Merenguelkl/Reverse_Disstilation community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
model.py ran fingerprinted no licence file found · pointer only · 6e7469746fc85cb1 · report fixture: returned ConvBlock · level recorded 2026-09-22
ConvTransposeBlock model.py ran fingerprinted no licence file found · pointer only · 5063a4c43a1a7153 · report fixture: returned ConvTransposeBlock · level recorded 2026-09-22
Decoder in 210 papers model.py ran no licence file found · pointer only · 38c83c026aa86db5 · report fixture: returned Decoder · level recorded 2026-09-22
IndentityBlock model.py ran fingerprinted no licence file found · pointer only · 214139d28682c605 · report fixture: returned IndentityBlock · level recorded 2026-09-22
OCBE model.py ran no licence file found · pointer only · 9d92e02d06b0fcdc · report fixture: signature x1:Tensor/4/float, x2:Tensor/4/float, x3:Tensor/4/float · returned Tensor · level recorded 2026-09-24
OcbeAndDecoder model.py unverified no licence file found · pointer only · b647c54316ac9330 · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv1x1 in 691 papers repository not located ran · our draft was wrong licence of this copy not recorded · 2a80220dabcb742a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers repository not located ran · our draft was wrong licence of this copy not recorded · 600ff2c45e0de056 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for Reverse Distillation (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Reverse Distillation (graph method: Reverse Distillation). 7 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. deResNet entry · level 1 · ran · 274a066ad1685214
  2. deBasicBlock model · level 1 · ran · 3f0806f63aee3bdd
  3. deBottleneck model · level 0 · unverified · 1e173e8f7793f155
  4. deconv2x2 helper · level 1 · ran · our draft was wrong · 8d035278d5e4a82a
  5. init_weights helper · level 1 · ran · our draft was wrong · 5c6ddf757751d73a
  6. conv3x3 helper · level 1 · ran · our draft was wrong · 600ff2c45e0de056
  7. conv1x1 helper · level 1 · ran · our draft was wrong · 2a80220dabcb742a

harvested Assembly for Reverse Distillation (graph method: Reverse Distillation). 6 bricks; individually on a fixture: 5 ran (of which 4 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. The assembly has not been run end-to-end.

one of 4 siblings

  1. OcbeAndDecoder entry · level 0 · unverified · b647c54316ac9330
  2. Decoder model · level 1 · ran · 38c83c026aa86db5
  3. OCBE model · level 1 · ran · 9d92e02d06b0fcdc
  4. ConvTransposeBlock helper · level 1 · ran · 5063a4c43a1a7153
  5. IndentityBlock helper · level 1 · ran · 214139d28682c605
  6. ConvBlock helper · level 1 · ran · 6e7469746fc85cb1

harvested Assembly for Reverse Distillation (graph method: Reverse Distillation). 6 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ResNet entry · level 0 · unverified · 6f9abfc5f148cc04
  2. BasicBlock model · level 1 · ran · ce529f9eb01d326b
  3. Bottleneck model · level 1 · ran · 2d33e6c48f4a2845
  4. deconv2x2 helper · level 1 · ran · our draft was wrong · 8d035278d5e4a82a
  5. conv3x3 helper · level 1 · ran · our draft was wrong · 600ff2c45e0de056
  6. conv1x1 helper · level 1 · ran · our draft was wrong · 2a80220dabcb742a

harvested Assembly for Reverse Distillation (graph method: Reverse Distillation). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ResNet entry · level 0 · unverified · c27cbb6fba18f4ba
  2. deBasicBlock model · level 1 · ran · 3f0806f63aee3bdd
  3. deBottleneck model · level 0 · unverified · 1e173e8f7793f155
  4. deconv2x2 helper · level 1 · ran · our draft was wrong · 8d035278d5e4a82a
  5. memoryModule helper · level 1 · ran · ddda7402c136e2b4
  6. conv3x3 helper · level 1 · ran · our draft was wrong · 600ff2c45e0de056
  7. conv1x1 helper · level 1 · ran · our draft was wrong · 2a80220dabcb742a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2201.10703") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly ClassificationAnomaly DetectionAnomaly SegmentationDecoderDiversityKnowledge DistillationNovelty DetectionUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Classification GoodsAD RD4AD AUPR 68.2 #8 of 11 Archive leaderboard report
Anomaly Classification GoodsAD RD4AD AUROC 66.5 #8 of 11 Archive leaderboard report
Anomaly Detection AeBAD-S ReverseDistillation Detection AUROC 81.0 #3 of 8 Archive leaderboard report
Anomaly Detection AeBAD-S ReverseDistillation Segmentation AUPRO 85.6 #3 of 8 Archive leaderboard report
Anomaly Detection AeBAD-V ReverseDistillation Detection AUROC 71.0 #2 of 7 Archive leaderboard report
Anomaly Detection Fashion-MNIST Reverse Distillation ROC AUC 95.0 #3 of 12 Archive leaderboard report
Anomaly Detection MVTec AD Reverse Distillation Detection AUROC 98.5 #57 of 148 Archive leaderboard report
Anomaly Detection MVTec AD Reverse Distillation Segmentation AUPRO 93.9 #57 of 148 Archive leaderboard report
Anomaly Detection MVTec AD Reverse Distillation Segmentation AUROC 97.8 #57 of 148 Archive leaderboard report
Anomaly Detection MVTec LOCO AD RD4AD Avg. Detection AUROC 78.7 #29 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD RD4AD Detection AUROC (only logical) 69.4 #29 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD RD4AD Detection AUROC (only structural) 88.0 #29 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD RD4AD Segmentation AU-sPRO (until FPR 5%) 63.7 #29 of 40 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 Reverse Distillation AUROC 86.5 #24 of 36 Archive leaderboard report
Anomaly Detection VisA Reverse Distillation Segmentation AUPRO (until 30% FPR) 70.9 #45 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

Knowledge Distillation

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