An Acceleration Method Based on Deep Learning and Multilinear Feature Space

TL;DR

This paper introduces AMFC, a transfer learning-based method using multilinear feature space to significantly accelerate CNN-based image classification, achieving 17 times faster results with minimal accuracy loss for embedded systems.

Contribution

The paper proposes a novel approach that leverages multilinear feature space and transfer learning to drastically reduce classification time of CNNs in embedded applications.

Findings

AMFC achieves 17x faster classification than original CNNs.

The method maintains minimal accuracy loss.

Applicable to various CNN architectures like VGG-16.

Abstract

Computer vision plays a crucial role in Advanced Assistance Systems. Most computer vision systems are based on Deep Convolutional Neural Networks (deep CNN) architectures. However, the high computational resource to run a CNN algorithm is demanding. Therefore, the methods to speed up computation have become a relevant research issue. Even though several works on architecture reduction found in the literature have not yet been achieved satisfactory results for embedded real-time system applications. This paper presents an alternative approach based on the Multilinear Feature Space (MFS) method resorting to transfer learning from large CNN architectures. The proposed method uses CNNs to generate feature maps, although it does not work as complexity reduction approach. After the training process, the generated features maps are used to create vector feature space. We use this new vector space to make projections of any new sample to classify them. Our method, named AMFC, uses the transfer learning from pre-trained CNN to reduce the classification time of new sample image, with minimal accuracy loss. Our method uses the VGG-16 model as the base CNN architecture for experiments; however, the method works with any similar CNN model. Using the well-known Vehicle Image Database and the German Traffic Sign Recognition Benchmark, we compared the classification time of the original VGG-16 model with the AMFC method, and our method is, on average, 17 times faster. The fast classification time reduces the computational and memory demands in embedded applications requiring a large CNN architecture.