MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing
Abstract
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 reconstruction in optimization-inspired networks. In order to solve the above problems, we proposed MC-ISTA-Net
Cite
@article{arxiv.1902.09878,
title = {MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing},
author = {Nanyu Li and Cuiyin Liu},
journal= {arXiv preprint arXiv:1902.09878},
year = {2019}
}
Comments
We request withdraw this paper for the reasons stated as following. The paper is not published in any journal. Some errors and insufficient experiments are found in the recently work. The rectified work and relevant supplementary experiments will be done for this paper in the future. After these, we will submit the new version of this paper