Open AccessAn Acceleration Method based on Deep Learning and Multilinear Feature Space
Author(s) -
Michel Andre L. Vinagreiro,
Edson C. Kitani,
Armando Antônio Maria Laganá,
Leopoldo Rideki Yoshioka
Publication year - 2021
Publication title -
international journal of artificial intelligence and applications
Language(s) - English
Resource type - Journals
eISSN - 0976-2191
pISSN - 0975-900X
DOI - 10.5121/ijaia.2021.12502
Subject(s) - computer science , convolutional neural network , artificial intelligence , benchmark (surveying) , deep learning , feature vector , transfer of learning , feature (linguistics) , feature extraction , pattern recognition (psychology) , reduction (mathematics) , speedup , machine learning , parallel computing , linguistics , philosophy , geometry , mathematics , geodesy , geography
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 literaturehave not yet been achievedsatisfactory 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 AMFCmethod, 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.