Global Filter Networks for Image Classification Supplementary Material

In this section, we will elaborate on the derivation and the properties of the discrete Fourier transform. A.1 From Fourier transform to discrete Fourier transform Discrete Fourier transform (DFT) can be derived in many ways. Here we will introduce the formulation of DFT from the standard Fourier transform (FT), which is originally designed for continuous signals. The FT converts a continuous signal from the time domain to the frequency domain and can be viewed as an extension of the Fourier series. From the formulas of the FT and the IFT we can have a glimpse of the duality property of the FT between the time domain and the frequency domain.