Abstract
In this work, we propose a novel approach called Operational Support Estimator Networks (OSENs) for the support estimation task. Support Estimation (SE) is defined as finding the locations of non-zero elements in a sparse signal. By its very nature, the mapping between the measurement and sparse signal is a non-linear operation. Traditional support estimators rely on computationally expensive iterative signal recovery techniques to achieve such non-linearity. Contrary to the convolution layers, the proposed OSEN approach consists of operational layers that can learn such complex non-linearities without the need for deep networks. In this way, the performance of the non-iterative support estimation is greatly improved. Moreover, the operational layers comprise so-called generative \textit{super neurons} with non-local kernels. The kernel location for each neuron/feature map is optimized jointly for the SE task during the training. We evaluate the OSENs in three different applications: i. support estimation from Compressive Sensing (CS) measurements, ii. representation-based classification, and iii. learning-aided CS reconstruction where the output of OSENs is used as prior knowledge to the CS algorithm for an enhanced reconstruction. Experimental results show that the proposed approach achieves computational efficiency and outperforms competing methods, especially at low measurement rates by a significant margin. The software implementation is publicly shared at this https URL.
Abstract (translated)
在本作品中,我们提出了一种名为操作支持估计器网络(osen)的新方法,用于支持估计任务。支持估计(SE)的定义是找到稀疏信号中的非零元素的位置。从特性的角度来看,测量和稀疏信号之间的映射是一种非线性操作。传统的支持估计方法依赖于计算代价高昂的迭代信号恢复技术来实现这种非线性。与卷积层相反,我们提出的osen方法包括操作层,这些操作层不需要深度网络就可以学习这些复杂的非线性特性。通过这种方式,非迭代的支持估计性能得到了极大的改善。此外,操作层由所谓的生成神经元(super neurons)组成的,这些神经元具有非局部Kernel。每个神经元/特征映射的Kernel位置在训练期间 jointly 用于支持估计任务。我们在不同的应用程序中评估了osen:i.从压缩感知测量(CS)测量中进行支持估计,ii.基于表示的分类,以及iii.学习辅助的CS重构,其中osen的输出被用作CS算法的前置知识,以增强重构。实验结果表明,我们提出的方法实现了计算效率,并比竞争方法更有效,特别是在低测量率方面具有显著优势。软件实现在此httpsURL上公开分享。
URL
https://arxiv.org/abs/2307.06065
