An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination

TL;DR

EPHAD is a test-time adaptation framework that improves anomaly detection accuracy in contaminated datasets by integrating evidence from multimodal foundation models and classical methods, without requiring access to training pipelines.

Contribution

This work introduces EPHAD, a novel test-time adaptation method that enhances unsupervised anomaly detection in contaminated data without prior knowledge of contamination levels or access to training data.

Findings

EPHAD significantly improves detection accuracy across diverse datasets.

The framework is robust to varying contamination levels.

It is versatile across different anomaly detection models.

Abstract

Unsupervised anomaly detection (AD) methods typically assume clean training data, yet real-world datasets often contain undetected or mislabeled anomalies, leading to significant performance degradation. Existing solutions require access to the training pipelines, data or prior knowledge of the proportions of anomalies in the data, limiting their real-world applicability. To address this challenge, we propose EPHAD, a simple yet effective test-time adaptation framework that updates the outputs of AD models trained on contaminated datasets using evidence gathered at test time. Our approach integrates the prior knowledge captured by the AD model trained on contaminated datasets with evidence derived from multimodal foundation models like Contrastive Language-Image Pre-training (CLIP), classical AD methods like the Local Outlier Factor or domain-specific knowledge. We illustrate the intuition behind EPHAD using a synthetic toy example and validate its effectiveness through comprehensive experiments across eight visual AD datasets, twenty-six tabular AD datasets, and a real-world industrial AD dataset. Additionally, we conduct an ablation study to analyse hyperparameter influence and robustness to varying contamination levels, demonstrating the versatility and robustness of EPHAD across diverse AD models and evidence pairs. To ensure reproducibility, our code is publicly available at https://github.com/sukanyapatra1997/EPHAD.