Explainable Deep One-Class Classification

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.

PDF Abstract ICLR 2021 PDF ICLR 2021 Abstract

Results from the Paper


Ranked #5 on Anomaly Detection on One-class ImageNet-30 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection MVTec AD FCDD (semi-supervised) Segmentation AUROC 94 # 73
Anomaly Detection MVTec AD FCDD (unsupervised) Segmentation AUROC 88 # 84
Anomaly Detection One-class CIFAR-10 FCDD AUROC 92 # 14
Anomaly Detection One-class ImageNet-30 FCDD AUROC 91 # 5

Methods


No methods listed for this paper. Add relevant methods here