论文标题
快速分层深度展开网络用于图像压缩感应
Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing
论文作者
论文摘要
通过将某些优化求解器与深神经网络相结合，深层展开网络（DUN）近年来引起了图像压缩传感（CS）的广泛关注。但是，现有的DUN中仍然存在几个问题：1）对于每次迭代，通常采用一个简单的堆积卷积网络，这显然限制了这些模型的表现力。 2）培训完成后，对于任何输入内容，现有DUNS的大多数超参数都是固定的，这大大削弱了其适应性。在本文中，提出了通过展开快速迭代的收缩阈值算法（FISTA），这是一种新颖的快速分层dun，被称为Fhdun，是为图像压缩传感而提出的，其中开发了精心设计的层次结构，以合作探索富人的上下文，以探索丰富的富人上下文，以探索丰富的先验信息。为了进一步增强适应性，在我们的框架中开发了一系列的超参数生成网络，以根据输入内容动态生产相应的最佳超参数。此外，由于FISTA的加速政策，新嵌入的加速模块使拟议的Fhdun可为最近的Duns节省超过50％的迭代循环。广泛的CS实验表明，所提出的FHDUN优于现有的最新CS方法，同时保持较少的迭代。
By integrating certain optimization solvers with deep neural network, deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist several issues in existing DUNs: 1) For each iteration, a simple stacked convolutional network is usually adopted, which apparently limits the expressiveness of these models. 2) Once the training is completed, most hyperparameters of existing DUNs are fixed for any input content, which significantly weakens their adaptability. In this paper, by unfolding the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA), a novel fast hierarchical DUN, dubbed FHDUN, is proposed for image compressed sensing, in which a well-designed hierarchical unfolding architecture is developed to cooperatively explore richer contextual prior information in multi-scale spaces. To further enhance the adaptability, series of hyperparametric generation networks are developed in our framework to dynamically produce the corresponding optimal hyperparameters according to the input content. Furthermore, due to the accelerated policy in FISTA, the newly embedded acceleration module makes the proposed FHDUN save more than 50% of the iterative loops against recent DUNs. Extensive CS experiments manifest that the proposed FHDUN outperforms existing state-of-the-art CS methods, while maintaining fewer iterations.
