[Reproducibility Report] Explainable Deep One-Class Classification - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

[Reproducibility Report] Explainable Deep One-Class Classification

Résumé

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.

Dates et versions

hal-04319312 , version 1 (02-12-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

Citer

Joao P C Bertoldo, Etienne Decencière. [Reproducibility Report] Explainable Deep One-Class Classification. 2023. ⟨hal-04319312⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More