Boosting Anomaly Detection Using Unsupervised Diverse Test-Time Augmentation

TL;DR

This paper introduces TTAD, a novel test-time augmentation method for tabular anomaly detection that leverages synthetic neighbor-based augmentations and a Siamese network to improve detection accuracy, demonstrated by higher AUC scores.

Contribution

The paper proposes TTAD, the first TTA-based anomaly detection method for tabular data, using neighbor-based augmentation and a Siamese network for enhanced performance.

Findings

Achieved significantly higher AUC scores across all datasets.

Demonstrated effectiveness of neighbor-based augmentation methods like k-Means and SMOTE.

Validated the approach's superiority over existing methods.

Abstract

Anomaly detection is a well-known task that involves the identification of abnormal events that occur relatively infrequently. Methods for improving anomaly detection performance have been widely studied. However, no studies utilizing test-time augmentation (TTA) for anomaly detection in tabular data have been performed. TTA involves aggregating the predictions of several synthetic versions of a given test sample; TTA produces different points of view for a specific test instance and might decrease its prediction bias. We propose the Test-Time Augmentation for anomaly Detection (TTAD) technique, a TTA-based method aimed at improving anomaly detection performance. TTAD augments a test instance based on its nearest neighbors; various methods, including the k-Means centroid and SMOTE methods, are used to produce the augmentations. Our technique utilizes a Siamese network to learn an advanced distance metric when retrieving a test instance's neighbors. Our experiments show that the anomaly detector that uses our TTA technique achieved significantly higher AUC results on all datasets evaluated.