[Reproducibility Report] Explainable Deep One-Class Classification

Autor:	Bertoldo, Joao P. C., Decencière, Etienne
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Submitted to the ML Reproducibility Challenge 2021 Fall
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2206.02598 Zobrazit plný text záznamu View this record from Arxiv