SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12427 · ECCV · 2024

GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features

Cees Snoek, Efstratios Gavves, Yuki Asano, Mohammadreza Salehi, Luc Sträter

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2407.12427.json · badge: /api/ran/2407.12427.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
LucStrater/GeneralAD canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
img_to_patch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LucStrater/GeneralAD/src/kdad_vit.py
code served (permissive licence) · get_code("1659e3f998ab9a4f")
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 3, dtype family float, shape (2, 4, 12) 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

torch.manual_seed(0)

# Create a small image tensor [B, C, H, W]
# B=2 (batch), C=3 (channels), H=4 (height), W=4 (width)
x = torch.randn(2, 3, 4, 4)

# patch_size must divide H and W evenly
patch_size = 2

# flatten_channels can be True or False
flatten_channels = True

ARGS = {
    "x": x,
    "patch_size": patch_size,
    "flatten_channels": flatten_channels,
}
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 3, dtype family float, shape (2, 4, 12) — shape (2, 4, 12) 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
my_forward_wrapper Ran
ran; our contract draft was wrong, not the code
LucStrater/GeneralAD/src/general_ad.py
code served (permissive licence) · get_code("21752628f1cd7a55")
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 function. 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)

class SimpleAttention(nn.Module):
    def __init__(self, dim=4, num_heads=2):
        super().__init__()
        self.num_heads = num_heads
        self.dim = dim
        self.scale = (dim // num_heads) ** -0.5
        
        # qkv projects input to 3*dim
        self.qkv = nn.Linear(dim, 3 * dim)
        # proj projects output back to dim
        self.proj = nn.Linear(dim, dim)
        # dropout layers
        self.attn_drop = nn.Dropout(0.1)
        self.proj_drop = nn.Dropout(0.1)
        
        # will store attention map
        self.attn_map = None

# Create attention object
attn_obj = SimpleAttention(dim=4, num_heads=2)

ARGS = {
    "attn_obj": attn_obj
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
unnormalize Ran
ran; our contract draft was wrong, not the code
LucStrater/GeneralAD/src/run_viz.py
code served (permissive licence) · get_code("d4638a9a079ae91e")
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 2, dtype family float, shape (3, 4) 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

torch.manual_seed(0)

# Create a tensor with shape (3, 4) to represent normalized image data
# The function iterates over the first dimension (channels), so we need 3 channels
tensor = torch.randn(3, 4)

# Standard ImageNet normalization mean and std
mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)

ARGS = {
    "tensor": tensor,
    "mean": mean,
    "std": std
}
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 2, dtype family float, shape (3, 4) — shape (3, 4) 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
prepare_loader Not yet run
unverified (harvested, no recorded run)
LucStrater/GeneralAD/src/load_data.py
code served (permissive licence) · get_code("7746444ad2554256")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training set, like unseen objects in self-driving cars. In contrast, industrial anomalies are subtle defects that preserve semantic meaning, such as cracks in airplane components. In this paper, we present GeneralAD, an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings with minimal per-task adjustments. In our approach, we capitalize on the inherent design of Vision Transformers, which are trained on image patches, thereby ensuring that the last hidden states retain a patch-based structure. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features to construct pseudo-abnormal samples. These features are fed to an attention-based discriminator, which is trained to score every patch in the image. With this, our method can both accurately identify anomalies at the image level and also generate interpretable anomaly maps. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining for both localization and detection tasks. Code available at https://github.com/LucStrater/GeneralAD.

For agents

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

get_harvested_code_for_paper("2407.12427")
get_code_for_paper("2407.12427")
have("2407.12427")

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

curl https://syntology.ai/api/ran/2407.12427.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.12427.svg)](https://syntology.ai/paper/2407.12427)

Connect an agent — have() is free.