| Paper ID | MLSP-1.3 |
| Paper Title |
DEEP TRANSFORM AND METRIC LEARNING NETWORKS |
| Authors |
Wen Tang, North Carolina State University, United States; Emilie Chouzenoux, Jean-Christophe Pesquet, CentraleSupélec, France; Hamid Krim, North Carolina State University, United States |
| Session | MLSP-1: Deep Learning Training Methods 1 |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer dictionaries, the recently improved Deep DL methods have also fallen short on a number of issues. We hence propose a novel Deep DL approach where each DL layer can be formulated and solved as a combination of one linear layer and a Recurrent Neural Net- work, where the RNN is flexibly regraded as a layer-associated learned metric. Our proposed work unveils new insights be- tween the Neural Networks and Deep DL, and provides a novel, efficient and competitive approach to jointly learn the deep transforms and metrics. Extensive experiments are carried out to demonstrate that the proposed method can not only outperform existing Deep DL, but also state-of-the-art generic Convolutional Neural Networks. |
