ADMM-DAD Net: A Deep Unfolding Network for Analysis Compressed Sensing

IEEE International Conference on Acoustics Speech and Signal Processing, pp. 1506–1510

Abstract

In this paper, we propose a new deep unfolding neural network based on the ADMM algorithm for analysis Compressed Sensing. The proposed network jointly learns a redundant analysis operator for sparsification and reconstructs the signal of interest. We compare our proposed network with a state-of-the-art unfolded ISTA decoder, that also learns an orthogonal sparsifier. Moreover, we consider not only image, but also speech datasets as test examples. Computational experiments demonstrate that our proposed network outperforms the state-of-the-art deep unfolding network, consistently for both real-world image and speech datasets.

Authors 4

1. Vicky Kouni

   National and Kapodistrian University of Athens

   Affiliation as printed

   National & Kapodistrian University of Athens,Dep. of Informatics and Telecommunications,Greece

2. Georgios Paraskevopoulos

   National Technical University of Athens · Athena Research and Innovation Center In Information Communication & Knowledge Technologies

   Affiliation as printed

   National Technical University of Athens,School of Electrical & Computer Engineering,Greece

   Institute for Language & Speech Processing, Athena Research Center, Athens, Greece

3. Holger Rauhut Aachen Chair for Mathematics of Information Processing

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Chair for Mathematics of Information Processing,Germany

   Chair for Mathematics of Information Processing, RWTH Aachen University, Germany

4. George C. Alexandropoulos

   National and Kapodistrian University of Athens

   Affiliation as printed

   National & Kapodistrian University of Athens,Dep. of Informatics and Telecommunications,Greece