Computational optimization of convolutional neural networks using separated filters architecture

02/18/2020
by   Elena Limonova, et al.
0

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding, for example for recognition on mobile platforms or in embedded systems. In this paper we propose CNN structure transformation which expresses 2D convolution filters as a linear combination of separable filters. It allows to obtain separated convolutional filters by standard training algorithms. We study the computation efficiency of this structure transformation and suggest fast implementation easily handled by CPU or GPU. We demonstrate that CNNs designed for letter and digit recognition of proposed structure show 15 accuracy loss in industrial image recognition system. In conclusion, we discuss the question of possible accuracy decrease and the application of proposed transformation to different recognition problems. convolutional neural networks, computational optimization, separable filters, complexity reduction.

READ FULL TEXT
research
09/30/2015

Fast Algorithms for Convolutional Neural Networks

Deep convolutional neural networks take GPU days of compute time to trai...
research
02/02/2021

Orientation Convolutional Networks for Image Recognition

Deep Convolutional Neural Networks (DCNNs) are capable of obtaining powe...
research
07/15/2017

Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration

State-of-the-art convolutional neural networks are enormously costly in ...
research
06/25/2021

LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy

Light binary convolutional neural networks (LB-CNN) are particularly use...
research
12/04/2014

Convolutional Neural Networks at Constrained Time Cost

Though recent advanced convolutional neural networks (CNNs) have been im...
research
10/08/2020

Fast Fourier Transformation for Optimizing Convolutional Neural Networks in Object Recognition

This paper proposes to use Fast Fourier Transformation-based U-Net (a re...
research
10/21/2019

Separable Convolutional Eigen-Filters (SCEF): Building Efficient CNNs Using Redundancy Analysis

The high model complexity of deep learning algorithms enables remarkable...

Please sign up or login with your details

Forgot password? Click here to reset