Deep Dictionary Learning: A PARametric NETwork Approach
Artikel i vetenskaplig tidskrift, 2019

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The dictionaries and classification parameters are trained by a classification objective, and the sparse features are extracted by reducing a reconstruction loss in each layer. The reconstruction objectives in some sense regularize the classification problem and inject source signal information in the extracted features. The performance of the proposed hierarchical method increases by adding more layers, which consequently makes this model easier to tune and adapt. The proposed algorithm furthermore shows a remarkably lower fooling rate in the presence of adversarial perturbation. The validation of the proposed approach is based on its classification performance using four benchmark datasets and is compared to a Convolutional Neural Network (CNN) of similar size.

Författare

Shahin Mahdizadehaghdam

North Carolina State University

Ashkan Panahi

North Carolina State University

Hamid Krim

North Carolina State University

Liyi Dai

Raytheon

IEEE Transactions on Image Processing

1057-7149 (ISSN) 19410042 (eISSN)

Vol. 28 10 4790-4802 18882074

Ämneskategorier

Reglerteknik

Signalbehandling

Datavetenskap (datalogi)

DOI

10.1109/TIP.2019.2914376

Mer information

Senast uppdaterat

2021-03-08