SeKron: A Decomposition Method Supporting Many Factorization Structures

no code implementations • 12 Oct 2022 • Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei, Vahid Partovi Nia

We validate SeKron for model compression on both high-level and low-level computer vision tasks and find that it outperforms state-of-the-art decomposition methods.

Model Compression Tensor Decomposition

Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition

no code implementations • 29 Sep 2021 • Marawan Gamal Abdel Hameed, Marzieh S. Tahaei, Ali Mosleh, Vahid Partovi Nia

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.

Image Classification Knowledge Distillation +1