Tensor network compressibility of convolutional models

arXiv:2403.14379v1 Announce Type: cross
Abstract: Convolutional neural networks (CNNs) represent one of the most widely used neural network architectures, showcasing state-of-the-art performance in computer vision tasks. Although larger CNNs generally exhibit higher accuracy, their size can be effectively reduced by "tensorization" while maintaining accuracy. Tensorization consists of replacing the convolution kernels with compact decompositions such as Tucker, Canonical Polyadic decompositions, or quantum-inspired decompositions such as matrix product states, and directly training the factors in the decompositions to bias the learning …

abstract accuracy architectures art arxiv cnns computer computer vision convolution convolutional neural networks cs.cv cs.lg network networks neural network neural networks performance quant-ph state tasks tensor type vision