all AI news
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition. (arXiv:2109.14710v2 [cs.CV] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Modern Convolutional Neural Network (CNN) architectures, despite their
superiority in solving various problems, are generally too large to be deployed
on resource constrained edge devices. In this paper, we reduce memory usage and
floating-point operations required by convolutional layers in CNNs. We compress
these layers by generalizing the Kronecker Product Decomposition to apply to
multidimensional tensors, leading to the Generalized Kronecker Product
Decomposition (GKPD). Our approach yields a plug-and-play module that can be
used as a drop-in replacement for any …
arxiv compression convolutional neural network cv network neural network product