Using Multilinear Feature Space to Accelerate CNN Classification

Abstract

Computer vision plays a crucial role in ADAS security and navigation, as most systems are based on deep CNN architectures the 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 acceleration techniques 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. When the training process ends, the generated maps are used to create vector feature space. We use this new vector space to make projections of any new sample in order to classify them. Our method, named MFS-CNN, uses the transfer learning from pre trained CNN to reduce the classification time of new sample image, with minimal loss in accuracy. 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 original VGG-16 model with the MFS-CNN method and our method is, on average, 17 times faster. The fast classification time reduces the computational and memories demand in embedded applications that requires a large CNN architecture.