Explainable Deep One-Class Classification
This addresses the challenge of explainability in anomaly detection for applications like manufacturing, where understanding model decisions is crucial, though it is incremental in combining existing concepts.
The paper tackles the problem of interpreting deep one-class classification models for anomaly detection by introducing Fully Convolutional Data Description (FCDD), which generates explanation heatmaps directly from mapped samples, achieving competitive detection performance on benchmarks like CIFAR-10 and ImageNet and setting a new state of the art on MVTec-AD in the unsupervised setting.
Deep one-class classification variants for anomaly detection learn a mapping that concentrates nominal samples in feature space causing anomalies to be mapped away. Because this transformation is highly non-linear, finding interpretations poses a significant challenge. In this paper we present an explainable deep one-class classification method, Fully Convolutional Data Description (FCDD), where the mapped samples are themselves also an explanation heatmap. FCDD yields competitive detection performance and provides reasonable explanations on common anomaly detection benchmarks with CIFAR-10 and ImageNet. On MVTec-AD, a recent manufacturing dataset offering ground-truth anomaly maps, FCDD sets a new state of the art in the unsupervised setting. Our method can incorporate ground-truth anomaly maps during training and using even a few of these (~5) improves performance significantly. Finally, using FCDD's explanations we demonstrate the vulnerability of deep one-class classification models to spurious image features such as image watermarks.