ButterflyNet2D: Bridging Classical Methods and Neural Network Methods in Image Processing

Author name not available (Why is that?)

Publication date: 29 November 2022

Abstract: 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.

Has companion code repository: https://github.com/genz17/butterflynet2d

This page was built for publication: ButterflyNet2D: Bridging Classical Methods and Neural Network Methods in Image Processing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6418972)