论文标题
ButterflyNet2D：图像处理中的桥接经典方法和神经网络方法
ButterflyNet2D: Bridging Classical Methods and Neural Network Methods in Image Processing
论文作者
论文摘要
经典的基于傅立叶变换的方法和神经网络方法都广泛用于图像处理任务。前者具有更好的解释性，而后者通常在实践中取得更好的表现。本文介绍了蝴蝶Net2D，这是一种常规的CNN，具有稀疏的跨通道连接。提出了蝴蝶NET2D的傅立叶初始化策略，以近似傅立叶变换。数值实验验证了蝴蝶NET2D的准确性，近似于傅立叶和逆傅立叶变换。此外，通过四个图像处理任务和图像数据集，我们表明傅立叶初始化的butterflynet2d确实比随机初始化的神经网络获得了更好的性能。
Both classical Fourier transform-based methods and neural network methods are widely used in image processing tasks. The former has better interpretability, whereas the latter often achieves better performance in practice. This paper introduces ButterflyNet2D, a regular CNN with sparse cross-channel connections. A Fourier initialization strategy for ButterflyNet2D is proposed to approximate Fourier transforms. Numerical experiments validate the accuracy of ButterflyNet2D approximating both the Fourier and the inverse Fourier transforms. Moreover, through four image processing tasks and image datasets, we show that training ButterflyNet2D from Fourier initialization does achieve better performance than random initialized neural networks.
