Efficient Higher-order Convolution for Small Kernels in Deep Learning

arXiv:2404.16380v1 Announce Type: new
Abstract: Deep convolutional neural networks (DCNNs) are a class of artificial neural networks, primarily for computer vision tasks such as segmentation and classification. Many nonlinear operations, such as activation functions and pooling strategies, are used in DCNNs to enhance their ability to process different signals with different tasks. Conceptional convolution, a linear filter, is the essential component of DCNNs while nonlinear convolution is generally implemented as higher-order Volterra filters, However, for Volterra filtering, significant memory and …

arxiv convolution cs.cv deep learning small type