arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.10739cs.CVcs.LG
收藏

傅立叶特征让网络在低维域中学习高频函数

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

University of California, Berkeley(加州大学伯克利分校);Google Research(谷歌研究院);University of California, San Diego(加州大学圣地亚哥分校)

Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, Ren Ng

摘要:

我们表明,通过一个简单的傅立叶特征映射输入点,使多层感知器(MLP)学习低维问题域中的高频函数。这些结果揭示了计算机视觉和图形学的最新进展,这些进展通过使用MLP来表示复杂的3D对象和场景来实现最先进的结果。使用神经切线核(NTK)文献中的工具,我们证明了标准的MLP在理论和实践中都无法学习高频。为了克服这种光谱偏差,我们使用傅立叶特征映射将有效NTK转换为具有可调带宽的固定内核。我们提出了一种方法,用于选择特定问题的傅立叶特征,大大提高了性能的低维回归任务相关的计算机视觉和图形社区的MLP。

英文摘要:

We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results shed light on recent advances in computer vision and graphics that achieve state-of-the-art results by using MLPs to represent complex 3D objects and scenes. Using tools from the neural tangent kernel (NTK) literature, we show that a standard MLP fails to learn high frequencies both in theory and in practice. To overcome this spectral bias, we use a Fourier feature mapping to transform the effective NTK into a stationary kernel with a tunable bandwidth. We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑