Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification

TL;DR

This paper introduces a selective deep convolutional neural network that maintains high classification accuracy on distorted images while significantly reducing computational cost by using fewer parameters and operations.

Contribution

It proposes a novel neural network topology that achieves similar accuracy to state-of-the-art models at a lower computational and energy cost, especially for distorted images.

Findings

Achieves comparable accuracy with fewer parameters.

Reduces multiply-accumulate operations and energy consumption.

Enhances performance by combining with existing cost reduction methods.

Abstract

Deep convolutional neural networks have proven to be well suited for image classification applications. However, if there is distortion in the image, the classification accuracy can be significantly degraded, even with state-of-the-art neural networks. The accuracy cannot be significantly improved by simply training with distorted images. Instead, this paper proposes a multiple neural network topology referred to as a selective deep convolutional neural network. By modifying existing state-of-the-art neural networks in the proposed manner, it is shown that a similar level of classification accuracy can be achieved, but at a significantly lower cost. The cost reduction is obtained primarily through the use of fewer weight parameters. Using fewer weights reduces the number of multiply-accumulate operations and also reduces the energy required for data accesses. Finally, it is shown that the effectiveness of the proposed selective deep convolutional neural network can be further improved by combining it with previously proposed network cost reduction methods.