Скачать или смотреть Towards Real Unsupervised Anomaly Detection via Confident Meta-Learning

ICCV 2025 — Towards Real Unsupervised Anomaly Detection via Confident Meta-Learning (CoMet)
Authors: Muhammad Aqeel, Shakiba Sharifi, Marco Cristani, Francesco Setti
Paper: https://arxiv.org/abs/2508.02293
Contact: [email protected]

Abstract:
So-called unsupervised anomaly detection is better described as semi supervised, as it assumes all training data
are nominal. This assumption simplifies training but requires manual data curation, introducing bias and limiting adaptability. We propose Confident Meta-learning
(CoMet), a novel training strategy that enables deep
anomaly detection models to learn from uncurated datasets
where nominal and anomalous samples coexist, eliminating the need for explicit filtering. Our approach integrates
Soft Confident Learning, which assigns lower weights to
low-confidence samples, and Meta-Learning, which stabilizes training by regularizing updates based on trainingvalidation loss covariance. This prevents overfitting and enhances robustness to noisy data. CoMet is model-agnostic
and can be applied to any anomaly detection method trainable via gradient descent. Experiments on MVTec-AD,
VIADUCT, and KSDD2 with two state-of-the-art models
demonstrate the effectiveness of our approach, consistently
improving over the baseline methods, remaining insensitive
to anomalies in the training set, and setting a new state-ofthe-art across all datasets.

Datasets: MVTec-AD, VIADUCT, KSDD2
Keywords: Unsupervised anomaly detection, Meta-learning, Soft Confident Learning, Industrial inspection, Robust training

BibTeX
@inproceedings{aqeel2025CoMet,
title={Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning},
author={Aqeel, Muhammad and Sharifi, Shakiba and Cristani, Marco and Setti, Francesco},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
year={2025},
}