Computational optimization of convolutional neural networks using separated filters architecture

TL;DR

This paper introduces a CNN transformation using separable filters that reduces computational complexity and speeds up processing by 15% without losing accuracy, suitable for image recognition tasks.

Contribution

It proposes a novel CNN structure transformation expressing 2D filters as linear combinations of separable filters, enabling faster computation with standard training algorithms.

Findings

Achieved 15% speedup in CNN processing without accuracy loss.

Demonstrated effectiveness on letter and digit recognition tasks.

Discussed potential for applying the method to various recognition problems.

Abstract

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% speedup without 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.