Spatially-weighted Anomaly Detection with Regression Model

TL;DR

This paper introduces a novel spatially-weighted anomaly detection method using a regression model and visualization-based region of interest, demonstrating superior performance over existing methods across multiple datasets.

Contribution

The paper proposes a new spatially-weighted reconstruction-loss-based anomaly detection approach that leverages visualization for region weighting and combines various strategies for improved robustness.

Findings

Outperforms existing anomaly detection methods on three datasets

Utilizes visualization to generate spatial weights for anomaly localization

Demonstrates robustness to noise and availability of some anomaly samples

Abstract

Visual anomaly detection is common in several applications including medical screening and production quality check. Although a definition of the anomaly is an unknown trend in data, in many cases some hints or samples of the anomaly class can be given in advance. Conventional methods cannot use the available anomaly data, and also do not have a robustness of noise. In this paper, we propose a novel spatially-weighted reconstruction-loss-based anomaly detection with a likelihood value from a regression model trained by all known data. The spatial weights are calculated by a region of interest generated from employing visualization of the regression model. We introduce some ways to combine with various strategies to propose a state-of-the-art method. Comparing with other methods on three different datasets, we empirically verify the proposed method performs better than the others.