Compressing convolutional neural networks with hierarchical Tucker-2 decomposition

M Gabor, R Zdunek - Applied Soft Computing, 2023 - Elsevier
Convolutional neural networks (CNNs) play a crucial role and achieve top results in
computer vision tasks but at the cost of high computational cost and storage complexity. One …

ELRT: Towards Efficient Low-Rank Training for Compact Neural Networks

Y Sui, M Yin, W Yang, Y Gong, J **ao, H Phan, D Ding… - openreview.net
Low-rank compression, a popular model compression technique that produces compact
convolutional neural networks (CNNs) with low rankness, has been well studied in the …