建筑-不可知无训练网络Priors用于图像重建与频率调节规范化
Yilin Liu1, Yunkui Pang1, Jiang Li1
1Computer Science, University of North Carolina at Chapel Hill.
概括
没有训练的深度学习网络现在可以在没有训练数据的情况下恢复高质量的图像. 新的方法有效地控制网络光谱偏差,减少过拟合,改善MRI重建等任务的性能.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 医疗成像医学成像
背景情况:
- 未经训练的网络利用深度图像先验来进行图像恢复,而无需训练集.
- 成功与网络架构中的光谱偏差有关,作为隐含的规范化.
- 当前的方法面临着诸如架构过度规范,过度装配和长时间优化等挑战.
研究的目的:
- 开发高效的,建筑不可知的技术,直接调节网络先验的光谱偏差.
- 为了应对未经训练的网络应用程序中过度安装和漫长优化的挑战.
- 为了实现使用紧型号,缩短运行时间,以获得更优异或可比性能.
主要方法:
- 实施带宽受限制的输入.
- 集成带宽可控制的上采样器.
- 应用Lipschitz规则化的卷积层.
主要成果:
- 在表现不佳的架构中,证明了过度装配的减少.
- 关闭不同网络架构之间的性能差距,最小的代码更改.
- 通过使用更紧的模型与更短的运行时间实现了可比或更优异的性能.
- 成功应用于像绘画一样的MRI重建任务.
结论:
- 在未经训练的网络前置中,架构偏差,过度装配和运行时间问题可以在没有架构修改的情况下同时解决.
- 提出的技术为提高未经训练的网络性能提供了有效和实际的解决方案.
- 这些发现为基于深度学习的更容易访问和更有效的图像重建铺平了道路.
相关概念视频
Reconstruction of Signal using Interpolation
136
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
136
Aliasing
100
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
100


