Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning

TL;DR

This paper introduces CoMet, a novel meta-learning approach for unsupervised anomaly detection that effectively learns from uncurated data containing both nominal and anomalous samples, improving robustness and accuracy.

Contribution

We propose Confident Meta-learning (CoMet), a new training strategy combining Soft Confident Learning and Meta-Learning to enable anomaly detection models to learn from unfiltered, noisy datasets.

Findings

Consistently improves baseline models on multiple datasets.

Remains insensitive to anomalies in training data.

Sets new state-of-the-art performance across datasets.

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 training validation 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-of-the-art across all datasets. Code is available at https://github.com/aqeeelmirza/CoMet