MC-ISTA-Net：受自适应测量与初始化及通道注意力优化启发的压缩感知神经网络
计算机视觉与模式识别
2019-08-13 v3
摘要
受优化启发的网络能够在自然图像压缩感知（CS）重建中桥接凸优化与神经网络，例如 ISTA-Net+，其将优化算法——迭代收缩阈值算法（ISTA）——映射为网络。然而，测量矩阵与输入初始化仍是手工设计的，且多通道特征图包含不同频率的信息，在通道间被平等对待，阻碍了优化启发网络在 CS 重建中的能力。为解决上述问题，我们提出了 MC-ISTA-Net。
引用
@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}
}
备注
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