Deep Dictionary Learning: A PARametric NETwork Approach
This work addresses image classification with a novel dictionary-based approach that offers better robustness to adversarial perturbations, though it appears incremental as an extension of dictionary learning methods.
The authors tackled image classification by proposing a hierarchical deep dictionary learning method that trains dictionaries and classification parameters jointly, achieving improved performance with more layers and showing lower vulnerability to adversarial attacks compared to CNNs of similar size.
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 remarkably lower fooling rate in 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 CNN of similar size.