• Corpus ID: 67855313

MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing

@article{Li2019MCISTANetAM,
  title={MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing},
  author={Nanyu Li and Cuiyin Liu and Wei Dai},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.09878}
}
The optimization inspired network can bridge convex optimization and neural networks in Compressive Sensing (CS) reconstruction of natural image, like ISTA-Net+, which mapping optimization algorithm: iterative shrinkage-thresholding algorithm (ISTA) into network. However, measurement matrix and input initialization are still hand-crafted, and multi-channel feature map contain information at different frequencies, which is treated equally across channels, hindering the ability of CS… 

References

SHOWING 1-10 OF 43 REFERENCES
ISTA-Net: Iterative Shrinkage-Thresholding Algorithm Inspired Deep Network for Image Compressive Sensing
TLDR
This paper proposes a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $l_1$ norm CS reconstruction model, and proposes an accelerated version of ISTA -Net, dubbed FISTA-Net , which isinspired by the fast iterative shrinkage-thresholding algorithm (FISTA).
Adaptive Measurement Network for CS Image Reconstruction
TLDR
An adaptive measurement network in which measurement is obtained by learning is proposed, which outperforms the original one and can extract the information of scene more efficiently and get better reconstruction results.
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements
TLDR
A novel convolutional neural network architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction which is fed into an off-the-shelf denoiser to obtain the final reconstructed image, ReconNet.
Deep ADMM-Net for Compressive Sensing MRI
TLDR
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements
TLDR
A novel convolutional neural network architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction which is fed into an off-the-shelf denoiser to obtain the final reconstructed image, ReconNet.
A deep learning approach to structured signal recovery
TLDR
A stacked denoising autoencoder is applied, as an unsupervised feature learner, to capture statistical dependencies between the different elements of certain signals and improve signal recovery performance as compared to the CS approach.
AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
TLDR
This paper proposes two novel neural-network architectures that decouple prediction errors across layers in the same way that the approximate message passing (AMP) algorithms decouple them across iterations: through Onsager correction.
Projected Iterative Soft-Thresholding Algorithm for Tight Frames in Compressed Sensing Magnetic Resonance Imaging
TLDR
It is proved that pISTA and pFISTA converge to a minimizer of a convex function with a balanced tight frame sparsity formulation, and leads to faster convergence speeds than the state-of-art counterpart does, while achieving comparable reconstruction errors.
Squeeze-and-Excitation Networks
TLDR
This work proposes a novel architectural unit, which is term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and shows that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets.
...
...