压缩传感
鉴别器
计算机科学
发电机(电路理论)
约束(计算机辅助设计)
过程(计算)
透视图(图形)
信号(编程语言)
人工智能
图像(数学)
利用
信号重构
人工神经网络
算法
模式识别(心理学)
信号处理
数学
操作系统
物理
探测器
功率(物理)
电信
程序设计语言
雷达
量子力学
计算机安全
几何学
作者
Yan Wu,Mihaela Rosca,Timothy Lillicrap
出处
期刊:Cornell University - arXiv
日期:2019-01-01
被引量:65
标识
DOI:10.48550/arxiv.1905.06723
摘要
Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and recover an image from only a few random measurements. CS is flexible and data efficient, but its application has been restricted by the strong assumption of sparsity and costly reconstruction process. A recent approach that combines CS with neural network generators has removed the constraint of sparsity, but reconstruction remains slow. Here we propose a novel framework that significantly improves both the performance and speed of signal recovery by jointly training a generator and the optimisation process for reconstruction via meta-learning. We explore training the measurements with different objectives, and derive a family of models based on minimising measurement errors. We show that Generative Adversarial Nets (GANs) can be viewed as a special case in this family of models. Borrowing insights from the CS perspective, we develop a novel way of improving GANs using gradient information from the discriminator.
科研通智能强力驱动
Strongly Powered by AbleSci AI