AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing
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.
PDF AbstractCode
Tasks
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Compressive Sensing | BSD68 CS=50% | AMPA-Net | Average PSNR | 36.33 | # 1 | |
Compressive Sensing | BSDS100 - 2x upscaling | AMPA-Net | Average PSNR | 35.95 | # 1 | |
Compressive Sensing | Set11 cs=50% | AMPA-Net | Average PSNR | 40.32 | # 1 | |
Compressive Sensing | Urban100 - 2x upscaling | AMPA-Net | Average PSNR | 35.86 | # 1 |