SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.03734 · ICLR · 2020

Iterative energy-based projection on a normal data manifold for anomaly localization

David Dehaene, Oriel Frigo, Sébastien Combrexelle, Pierre Eline

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2002.03734.json · badge: /api/ran/2002.03734.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
ForrestPi/anomalyLocalization community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
loss_function Ran
ran on a synthesized input
ForrestPi/anomalyLocalization/network.py
code served (permissive licence) · get_code("d25dc976c772c210")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create small tensors for a VAE loss function
# batch_size=2, latent_dim=4, data_dim=3
batch_size = 2
latent_dim = 4
data_dim = 3

# recon_x: reconstructed output from decoder, should be probabilities [0,1]
recon_x = torch.sigmoid(torch.randn(batch_size, data_dim))

# x: original input data, should be binary or in [0,1] for BCE
x = torch.randint(0, 2, (batch_size, data_dim)).float()

# mu: mean of latent distribution
mu = torch.randn(batch_size, latent_dim)

# logvar: log variance of latent distribution
logvar = torch.randn(batch_size, latent_dim)

ARGS = {
    "recon_x": recon_x,
    "x": x,
    "mu": mu,
    "logvar": logvar,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
return_MVTecAD_loader Ran
ran on a synthesized input
ForrestPi/anomalyLocalization/dataset.py
code served (permissive licence) · get_code("6d04dd9c3f9c8967")
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 DataLoader. 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 os
import tempfile
from PIL import Image
import torch
from torchvision import transforms as T

torch.manual_seed(0)

# Create a temporary directory with dummy PNG images
temp_dir = tempfile.mkdtemp()
for i in range(5):
    filename = os.path.join(temp_dir, '{:03d}.png'.format(i))
    img = Image.new('RGB', (256, 256), color=(73, 109, 137))
    img.save(filename)

ARGS = {
    'image_dir': temp_dir,
    'batch_size': 2,
    'train': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

Autoencoder reconstructions are widely used for the task of unsupervised anomaly localization. Indeed, an autoencoder trained on normal data is expected to only be able to reconstruct normal features of the data, allowing the segmentation of anomalous pixels in an image via a simple comparison between the image and its autoencoder reconstruction. In practice however, local defects added to a normal image can deteriorate the whole reconstruction, making this segmentation challenging. To tackle the issue, we propose in this paper a new approach for projecting anomalous data on a autoencoder-learned normal data manifold, by using gradient descent on an energy derived from the autoencoder's loss function. This energy can be augmented with regularization terms that model priors on what constitutes the user-defined optimal projection. By iteratively updating the input of the autoencoder, we bypass the loss of high-frequency information caused by the autoencoder bottleneck. This allows to produce images of higher quality than classic reconstructions. Our method achieves state-of-the-art results on various anomaly localization datasets. It also shows promising results at an inpainting task on the CelebA dataset.

For agents

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

get_harvested_code_for_paper("2002.03734")
get_code_for_paper("2002.03734")
have("2002.03734")

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

curl https://syntology.ai/api/ran/2002.03734.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.03734.svg)](https://syntology.ai/paper/2002.03734)

Connect an agent — have() is free.