SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.07849 · NeurIPS · 2023

Zero-Shot Anomaly Detection via Batch Normalization

Stephan Mandt, Marius Kloft, T Kaiserslautern, Padhraic Smyth, Chen Qiu, Maja Rudolph, Aodong Li, U Irvine

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has no contract verdict; 0 failures of our instrument; 0 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/2302.07849.json · badge: /api/ran/2302.07849.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
aodongli/zero-shot-ad-via-batch-norm canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
DCL Ran
ran on a synthesized input
aodongli/zero-shot-ad-via-batch-norm/anoshift-cifar100c-omniglot/losses/ntl_loss.py
code served (permissive licence) · get_code("47c477fbc4b5ecb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import torch.nn.functional as F
import numpy as np

class DCL(nn.Module):

    def __init__(self, config=None):
        super(DCL, self).__init__()
        self.temp = 0.1

    def forward(self, z, center):
        z = F.normalize(z, p=2, dim=-1)
        z_ori = z[:, 0]
        z_trans = z[:, 1:]
        batch_size, num_trans, z_dim = z.shape
        sim_matrix = torch.exp(torch.matmul(z, z.permute(0, 2, 1) / self.temp))
        mask = (torch.ones_like(sim_matrix).to(z) - torch.eye(num_trans).unsqueeze(0).to(z)).bool()
        sim_matrix = sim_matrix.masked_select(mask).view(batch_size, num_trans, -1)
        trans_matrix = sim_matrix[:, 1:].sum(-1)
        pos_sim = torch.exp(torch.sum(z_trans * z_ori.unsqueeze(1), -1) / self.temp)
        K = num_trans - 1
        scale = 1 / np.abs(np.log(1.0 / K))
        loss_tensor = (torch.log(trans_matrix) - torch.log(pos_sim)) * scale
        loss_n = loss_tensor.mean(1)
        loss_a = -torch.log(1 - pos_sim / trans_matrix) * scale
        loss_a = loss_a.mean(1)
        return (loss_n, loss_a)


INIT_ARGS = {
    'config': None
}

ARGS = {
    'z': torch.randn(2, 3, 4),
    'center': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = DCL(**INIT_ARGS)
    output = model(**ARGS)
    print("Output shapes:", [o.shape for o in output])
    print("Output:", output)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the "new normal", has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch normalization, enabling automatic zero-shot generalization for unseen AD tasks. This simple recipe, batch normalization plus meta-training, is a highly effective and versatile tool. Our theoretical results guarantee the zero-shot generalization for unseen AD tasks; our empirical results demonstrate the first zero-shot AD results for tabular data and outperform existing methods in zero-shot anomaly detection and segmentation on image data from specialized domains. Code is at https://github.com/aodongli/zero-shot-ad-via-batch-norm

For agents

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

get_harvested_code_for_paper("2302.07849")
get_code_for_paper("2302.07849")
have("2302.07849")

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

curl https://syntology.ai/api/ran/2302.07849.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.07849.svg)](https://syntology.ai/paper/2302.07849)

Connect an agent — have() is free.