Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation
This work addresses anomaly segmentation for image analysis, but it is incremental as it builds on existing methods.
The paper tackled the problem of adapting anomaly detection methods to image anomaly segmentation by proposing an incremental improvement to Fully Convolutional Data Description (FCDD) through a substitute loss function that better resembles the Hypersphere Classifier, resulting in consistent improvement on the MVTec Anomaly Detection Dataset.
We propose an incremental improvement to Fully Convolutional Data Description (FCDD), an adaptation of the one-class classification approach from anomaly detection to image anomaly segmentation (a.k.a. anomaly localization). We analyze its original loss function and propose a substitute that better resembles its predecessor, the Hypersphere Classifier (HSC). Both are compared on the MVTec Anomaly Detection Dataset (MVTec-AD) -- training images are flawless objects/textures and the goal is to segment unseen defects -- showing that consistent improvement is achieved by better designing the pixel-wise supervision.