Optimization-Inspired Compact Deep Compressive Sensing

In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Ne...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in signal processing 2020-05, Vol.14 (4), p.765-774
Main Authors: Zhang, Jian, Zhao, Chen, Gao, Wen
Format: Article
Language:English
Subjects:
Adaptive sampling
Adaptive systems
compressive sensing
Convolution
Design optimization
Dictionaries
Image enhancement
Image reconstruction
interpretable networks
neural networks
Optimization
Parameters
Recovery
Training
Transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Net simultaneously. In particular, OPINE-Net is composed of three subnets: sampling subnet, initialization subnet and recovery subnet, and all the parameters in OPINE-Net (e.g. sampling matrix, nonlinear transforms, shrinkage threshold) are learned end-to-end, rather than hand-crafted. Moreover, considering the relationship among neighboring blocks, an enhanced version OPINE-Net^+ is developed, which allows image blocks to be sampled independently but reconstructed jointly to further enhance the performance. In addition, some interesting findings of learned sampling matrix are presented. Compared with existing state-of-the-art network-based CS methods, the proposed hardware-friendly OPINE-Nets not only achieve better performance but also require much fewer parameters and much less storage space, while maintaining a real-time running speed.
ISSN:1932-4553
1941-0484
DOI:10.1109/JSTSP.2020.2977507