Classification-Based Anomaly Detection for General Data

TL;DR

This paper introduces GOAD, a classification-based open-set anomaly detection method that extends to various data types, achieving state-of-the-art accuracy across multiple domains.

Contribution

The paper presents GOAD, a novel open-set anomaly detection approach that generalizes transformation-based methods to non-image data and relaxes previous assumptions.

Findings

Achieves state-of-the-art accuracy on multiple datasets

Extends transformation-based methods to non-image data

Validated across diverse data domains

Abstract

Anomaly detection, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-based methods were shown to achieve superior results on this task. In this work, we present a unifying view and propose an open-set method, GOAD, to relax current generalization assumptions. Furthermore, we extend the applicability of transformation-based methods to non-image data using random affine transformations. Our method is shown to obtain state-of-the-art accuracy and is applicable to broad data types. The strong performance of our method is extensively validated on multiple datasets from different domains.