Fast Fourier Convolution - NIPS

← Back to document page

Fast Fourier ConvolutionLu Chi1, Borui Jiang2, Yadong Mu1 1Wangxuan Institute of Computer Technology,2Center for Data SciencePeking convolutions in modern deep networks are known to operate locally and atfixed scale ( , the widely-adopted3 3kernels in image-oriented tasks). Thiscauses low efficacy in connecting two distant locations in the network. In this work,we propose a novel convolutional operator dubbed asfast Fourier Convolution (FFC), which has the main hallmarks of non-local receptive fields and cross-scalefusion within the convolutional unit. According to spectral Convolution theorem inFourier theory, point-wise update in the spectral domain globally affects all inputfeatures involved in Fourier transform, which sheds light on neural architecturaldesign with non-local receptive field.

propagated features in a top-down manner, seamlessly bridging the high spatial resolution in lower layers and semantic discriminative ability in higher layers. Recently-proposed HRNet [29] conducted cross-scale fusion among multiple network branches that maintain different spatial resolutions. Spectral neural networks.

  Resolution, Spatial, Spectral, Spatial resolution