MOCCA: Multilayer one-class classification for anomaly detection
Published in IEEE Transactions on Neural Networks and Learning Systems, 2021
Recommended citation: F. V. Massoli, F. Falchi, A. Kantarci, Ş. Akti, H. K. Ekenel and G. Amato, "MOCCA: Multilayer One-Class Classification for Anomaly Detection," in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 6, pp. 2313-2323, June 2022, doi: 10.1109/TNNLS.2021.3130074. https://arxiv.org/pdf/2012.12111
We propose a novel framework, named multilayer one-class classification (MOCCA), to train and test deep learning models on the anomaly detection task. Code
Recommended citation: F. V. Massoli, F. Falchi, A. Kantarci, Ş. Akti, H. K. Ekenel and G. Amato, “MOCCA: Multilayer One-Class Classification for Anomaly Detection,” in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 6, pp. 2313-2323, June 2022, doi: 10.1109/TNNLS.2021.3130074.
