[Reproducibility Report] Explainable Deep One-Class Classification
This work addresses reproducibility and analysis for explainable anomaly detection in computer vision, but is incremental as it focuses on reproducing and extending prior research.
The paper reproduces Fully Convolutional Data Description (FCDD), an explainable deep one-class classification method for image anomaly detection, achieving results comparable to state-of-the-art on Fashion-MNIST and CIFAR-10 and exceeding it on MVTec-AD for pixel-wise tasks.
Fully Convolutional Data Description (FCDD), an explainable version of the Hypersphere Classifier (HSC), directly addresses image anomaly detection (AD) and pixel-wise AD without any post-hoc explainer methods. The authors claim that FCDD achieves results comparable with the state-of-the-art in sample-wise AD on Fashion-MNIST and CIFAR-10 and exceeds the state-of-the-art on the pixel-wise task on MVTec-AD. We reproduced the main results of the paper using the author's code with minor changes and provide runtime requirements to achieve if (CPU memory, GPU memory, and training time). We propose another analysis methodology using a critical difference diagram, and further investigate the test performance of the model during the training phase.