Explainable Deep One-Class Classification
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen et al. · arXiv (Cornell University) · 2020
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.
Cited by 98 works. doi:10.48550/arxiv.2007.01760 Open-access PDF
Authors
References
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Fully convolutional networks for semantic segmentation
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Learning Multiple Layers of Features from Tiny Images
- The Pascal Visual Object Classes (VOC) Challenge
- On the importance of initialization and momentum in deep learning
- Robust Estimation of a Location Parameter
- "Why Should I Trust You?"
- 80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition