AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing
This work addresses compressed sensing reconstruction for image processing applications, representing an incremental improvement by combining existing methods with attention mechanisms.
The authors tackled the problem of fast and accurate compressed sensing reconstruction in image processing by proposing AMP-Net, an optimization-inspired neural network based on the Approximate Message Passing algorithm, and AMPA-Net, which enhances it with attention networks, achieving state-of-the-art results on four benchmark datasets.
Compressed sensing (CS) is a challenging problem in image processing due to reconstructing an almost complete image from a limited measurement. To achieve fast and accurate CS reconstruction, we synthesize the advantages of two well-known methods (neural network and optimization algorithm) to propose a novel optimization inspired neural network which dubbed AMP-Net. AMP-Net realizes the fusion of the Approximate Message Passing (AMP) algorithm and neural network. All of its parameters are learned automatically. Furthermore, we propose an AMPA-Net which uses three attention networks to improve the representation ability of AMP-Net. Finally, We demonstrate the effectiveness of AMP-Net and AMPA-Net on four standard CS reconstruction benchmark data sets. Our code is available on https://github.com/puallee/AMPA-Net.