330 citations · 360 across the 5 of their papers we have counts for
Showing 2014Show all
2 papers · 1 filter
cs.CV2014★ 330 cited
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba +2
We propose a simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning. Gi…
math.NA2014★ 6 cited
Fast multidimensional convolution in low-rank formats via cross approximation
M. V. Rakhuba, I. V. Oseledets
We propose a new cross-conv algorithm for approximate computation of convolution in different low-rank tensor formats (tensor train, Tucker, Hierarchical Tucker). It has better com…