Year: 2018
Type: conference-paper
Abstract: In this paper, we present the deep sparse coding network (DSCN) - a novel deep learning framework that encodes intermediate representations with nonnegative sparse coding. DSCN is constructed from a cascade of bottleneck modules, each of which consists of two sparse coding layers with relatively wide and slim dictionaries that are specialized to produce high dimensional discriminative features and low dimensional clustered representations, respectively. During training, all dictionaries at all depth levels along with all regularization parameters are optimized jointly with an end-to-end supervised learning algorithm based on multilevel optimization. The effectiveness of the proposed DSCN with seven bottleneck modules11Consisting 14 sparse coding layers. is verified on several popular benchmark datasets Remarkably, with few parameters to learn, our SCN achieves 5.81 % and 19.93% classification error rate on CIFAR-10 and CIFAR-100, respectively.
Authors: Xiaoxia Sun, Nasser M. Nasrabadi, Trac D. Tran
Institutions: Johns Hopkins University, West Virginia University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2618372886
