SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.10703 · CVPR · 2022

Anomaly Detection via Reverse Distillation from One-Class Embedding

Xingyu Li, Hanqiu Deng

arXiv · PDF · Open in the Atlas

Code that ran

14 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 4 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2201.10703.json · badge: /api/ran/2201.10703.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Merenguelkl/Reverse_Disstilation community
Papers with Code archive
5 ran · 1 no recorded run
SimonThomine/DistillationAD community
Papers with Code archive
4 ran · 1 no recorded run
hq-deng/RD4AD marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
SimonThomine/RememberingNormality community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
hq-deng/RD4AD/de_resnet.py
code served (permissive licence) · get_code("ce529f9eb01d326b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, BasicBlock: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define a minimal upsample module that the BasicBlock might use
class MinimalUpsample(nn.Module):
    def forward(self, x):
        return x

# Build ARGS dict with all parameters for BasicBlock.__init__
ARGS = {
    'inplanes': 3,
    'planes': 4,
    'stride': 1,
    'upsample': None,
    'groups': 1,
    'base_width': 64,
    'dilation': 1,
    'norm_layer': nn.BatchNorm2d,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BasicBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BasicBlock output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
hq-deng/RD4AD/de_resnet.py
code served (permissive licence) · get_code("2d33e6c48f4a2845")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, Bottleneck: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define the upsample module that will be used in the Bottleneck
upsample_module = nn.Sequential(
    nn.Conv2d(64, 256, kernel_size=1, stride=1, bias=False),
    nn.BatchNorm2d(256)
)

ARGS = {
    'inplanes': 64,
    'planes': 64,
    'stride': 1,
    'upsample': upsample_module,
    'groups': 1,
    'base_width': 64,
    'dilation': 1,
    'norm_layer': nn.BatchNorm2d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Bottleneck — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Bottleneck output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ConvBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("6e7469746fc85cb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvTransposeBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("5063a4c43a1a7153")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Decoder Ran
ran on a synthesized input · constructed an object; no result was computed
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("38c83c026aa86db5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

IndentityBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("214139d28682c605")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

OCBE Ran
ran on a synthesized input
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("9d92e02d06b0fcdc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from medaitech/scrd4ad
pointer only; the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from medaitech/scrd4ad
pointer only; the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

deBasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
SimonThomine/DistillationAD/models/ReverseDistillation/de_resnet.py
pointer only (licence: NONE) · get_code("3f0806f63aee3bdd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/DistillationAD when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

deResNet Ran
ran on a synthesized input · constructed an object; no result was computed
SimonThomine/DistillationAD/models/ReverseDistillation/de_resnet.py
pointer only (licence: NONE) · get_code("274a066ad1685214")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/DistillationAD when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

deconv2x2 Ran
ran; our contract draft was wrong, not the code
SimonThomine/DistillationAD/models/ReverseDistillation/de_resnet.py
pointer only (licence: NONE) · get_code("8d035278d5e4a82a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/DistillationAD when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

init_weights Ran
ran; our contract draft was wrong, not the code
SimonThomine/DistillationAD/models/ReverseDistillation/de_resnet.py
pointer only (licence: NONE) · get_code("5c6ddf757751d73a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/DistillationAD when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

memoryModule Ran
ran on a synthesized input
SimonThomine/RememberingNormality/models/RD/de_resnetRM.py
pointer only (licence: NONE) · get_code("ddda7402c136e2b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/RememberingNormality when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

OcbeAndDecoder Not yet run
unverified (harvested, no recorded run)
Merenguelkl/Reverse_Disstilation/model.py
pointer only (licence: NONE) · get_code("b647c54316ac9330")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Merenguelkl/Reverse_Disstilation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ResNet Not yet run
unverified (harvested, no recorded run)
hq-deng/RD4AD/de_resnet.py
code served (permissive licence) · get_code("6f9abfc5f148cc04")
How it ran

no invocation recorded.

ResNet Not yet run
unverified (harvested, no recorded run)
SimonThomine/RememberingNormality/models/RD/de_resnetRM.py
pointer only (licence: NONE) · get_code("c27cbb6fba18f4ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/RememberingNormality when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

deBottleneck Not yet run
unverified (harvested, no recorded run)
SimonThomine/DistillationAD/models/ReverseDistillation/de_resnet.py
pointer only (licence: NONE) · get_code("1e173e8f7793f155")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SimonThomine/DistillationAD when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 3 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1
brick of this paper's assembly: helper
112 other papers
18 dated earlier, 1 the same month, 92 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3
brick of this paper's assembly: helper
111 other papers
16 dated earlier, 1 the same month, 93 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
deconv2x2
brick of this paper's assembly: helper
3 other papers
3 later
2405.14325 (2024-05)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
2503.02424 (2025-03)
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection
2503.13828 (2025-03)
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.10703")
get_code_for_paper("2201.10703")
have("2201.10703")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.10703.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.10703.svg)](https://syntology.ai/paper/2201.10703)

Connect an agent — have() is free.