NeoNeXt: Novel neural network operator and architecture based on the patch-wise matrix multiplications

arXiv:2403.11251v1 Announce Type: new
Abstract: Most of the computer vision architectures nowadays are built upon the well-known foundation operations: fully-connected layers, convolutions and multi-head self-attention blocks. In this paper we propose a novel foundation operation - NeoCell - which learns matrix patterns and performs patchwise matrix multiplications with the input data. The main advantages of the proposed operator are (1) simple implementation without need in operations like im2col, (2) low computational complexity (especially for large matrices) and (3) simple and …

abstract architecture architectures arxiv attention computer computer vision cs.cv foundation head matrix multi-head network neural network novel operations paper patterns self-attention type vision wise