Stable low-rank tensor decomposition for compression of convolutional neural network
Most state-of-the-art deep neural networks are overparameterized and exhibit a high
computational cost. A straightforward approach to this problem is to replace convolutional …
computational cost. A straightforward approach to this problem is to replace convolutional …
Few-bit backward: Quantized gradients of activation functions for memory footprint reduction
Memory footprint is one of the main limiting factors for large neural network training. In
backpropagation, one needs to store the input to each operation in the computational graph …
backpropagation, one needs to store the input to each operation in the computational graph …
How to train unstable looped tensor network
A rising problem in the compression of Deep Neural Networks is how to reduce the number
of parameters in convolutional kernels and the complexity of these layers by low-rank tensor …
of parameters in convolutional kernels and the complexity of these layers by low-rank tensor …
Mars: Masked automatic ranks selection in tensor decompositions
M Kodryan, D Kropotov… - … Conference on Artificial …, 2023 - proceedings.mlr.press
Tensor decomposition methods have proven effective in various applications, including
compression and acceleration of neural networks. At the same time, the problem of …
compression and acceleration of neural networks. At the same time, the problem of …
Connet: Designing a fast, efficient, and robust crowd counting model through composite compression
RMA Masilang, BJR Benedictos… - … Journal of Pattern …, 2023 - World Scientific
Counting the number of people in a specific area is crucial in maintaining proper crowd
safety and management especially in highly-congested indoor scenarios. Recent …
safety and management especially in highly-congested indoor scenarios. Recent …
[PDF][PDF] Learning Low-Rank Tensor Cores with Probabilistic l0-Regularized Rank Selection for Model Compression
Compressing deep neural networks is of great importance for real-world applications on
resourceconstrained devices. Tensor decomposition is one promising answer that retains …
resourceconstrained devices. Tensor decomposition is one promising answer that retains …