scholarly journals Stable Low-Rank Tensor Decomposition for Compression of Convolutional Neural Network

2020 ◽  
pp. 522-539
Author(s):  
Anh-Huy Phan ◽  
Konstantin Sobolev ◽  
Konstantin Sozykin ◽  
Dmitry Ermilov ◽  
Julia Gusak ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Tensor Decomposition ◽  
Low Rank ◽  
Rank Tensor

Learning a deep convolutional neural network via tensor decomposition

2021 ◽  
Author(s):  
Samet Oymak ◽  
Mahdi Soltanolkotabi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sample Size ◽  
Gaussian Distribution ◽  
Tensor Decomposition ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Low Rank ◽  
Rank Tensor

Abstract In this paper, we study the problem of learning the weights of a deep convolutional neural network. We consider a network where convolutions are carried out over non-overlapping patches. We develop an algorithm for simultaneously learning all the kernels from the training data. Our approach dubbed deep tensor decomposition (DeepTD) is based on a low-rank tensor decomposition. We theoretically investigate DeepTD under a realizable model for the training data where the inputs are chosen i.i.d. from a Gaussian distribution and the labels are generated according to planted convolutional kernels. We show that DeepTD is sample efficient and provably works as soon as the sample size exceeds the total number of convolutional weights in the network.

scholarly journals Low-Rank and Sparse Based Deep-Fusion Convolutional Neural Network for Crowd Counting

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Siqi Tang ◽  
Zhisong Pan ◽  
Xingyu Zhou
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Regression Method ◽  
Low Rank ◽  
Counting Method ◽  
Direct Integral ◽  
Crowd Counting ◽  
Counting Methods ◽  
Density Map

This paper proposes an accurate crowd counting method based on convolutional neural network and low-rank and sparse structure. To this end, we firstly propose an effective deep-fusion convolutional neural network to promote the density map regression accuracy. Furthermore, we figure out that most of the existing CNN based crowd counting methods obtain overall counting by direct integral of estimated density map, which limits the accuracy of counting. Instead of direct integral, we adopt a regression method based on low-rank and sparse penalty to promote accuracy of the projection from density map to global counting. Experiments demonstrate the importance of such regression process on promoting the crowd counting performance. The proposed low-rank and sparse based deep-fusion convolutional neural network (LFCNN) outperforms existing crowd counting methods and achieves the state-of-the-art performance.

Total Variation Regularized Low-Rank Tensor Decomposition with nonlocal for single image denoising

2021 ◽  
Author(s):  
Shengchuan Li ◽  
Yanmei Wang ◽  
Qiong Luo ◽  
Kai Wang ◽  
Zhi Han ◽  
...  
Keyword(s):  
Image Denoising ◽  
Total Variation ◽  
Tensor Decomposition ◽  
Low Rank ◽  
Single Image ◽  
Rank Tensor

Multilayer Sparsity-Based Tensor Decomposition for Low-Rank Tensor Completion

2021 ◽  
pp. 1-15
Author(s):  
Jize Xue ◽  
Yongqiang Zhao ◽  
Shaoguang Huang ◽  
Wenzhi Liao ◽  
Jonathan Cheung-Wai Chan ◽  
...  
Keyword(s):  
Tensor Decomposition ◽  
Low Rank ◽  
Tensor Completion ◽  
Rank Tensor

Hyperspectral Image Restoration Using Weighted Group Sparsity-Regularized Low-Rank Tensor Decomposition

2020 ◽  
Vol 50 (8) ◽  
pp. 3556-3570 ◽  
Author(s):  
Yong Chen ◽  
Wei He ◽  
Naoto Yokoya ◽  
Ting-Zhu Huang
Keyword(s):  
Image Restoration ◽  
Hyperspectral Image ◽  
Tensor Decomposition ◽  
Low Rank ◽  
Group Sparsity ◽  
Rank Tensor

scholarly journals Object-Based Multipass InSAR via Robust Low-Rank Tensor Decomposition

2018 ◽  
Vol 56 (6) ◽  
pp. 3062-3077 ◽  
Author(s):  
Jian Kang ◽  
Yuanyuan Wang ◽  
Michael Schmitt ◽  
Xiao Xiang Zhu
Keyword(s):  
Tensor Decomposition ◽  
Low Rank ◽  
Rank Tensor ◽  
Object Based
Sign in / Sign up

Export Citation Format

Share Document