Please use this identifier to cite or link to this item:
http://repositorio.unicamp.br/jspui/handle/REPOSIP/320184
Type: | Artigo |
Title: | Rate-energy-accuracy optimization of convolutional architectures for face recognition |
Author: | Bondi, L. Baroffio, L. Cesana, M. Tagliasacchi, M. Chiachia, G. Rocha, A. |
Abstract: | Face recognition systems based on Convolutional Neural Networks (CNNs) or convolutional architectures currently represent the state of the art, achieving an accuracy comparable to that of humans. Nonetheless, there are two issues that might hinder their adoption on distributed battery-operated devices (e.g., visual sensor nodes, smartphones, and wearable devices). First, convolutional architectures are usually computationally demanding, especially when the depth of the network is increased to maximize accuracy. Second, transmitting the output features produced by a CNN might require a bitrate higher than the one needed for coding the input image. Therefore, in this paper we address the problem of optimizing the energy-rate-accuracy characteristics of a convolutional architecture for face recognition. We carefully profile a CNN implementation on a Raspberry Pi device and optimize the structure of the neural network, achieving a 17-fold speedup without significantly affecting recognition accuracy. Moreover, we propose a coding architecture custom-tailored to features extracted by such model. (C) 2015 Elsevier Inc. All rights reserved. Face recognition systems based on Convolutional Neural Networks (CNNs) or convolutional architectures currently represent the state of the art, achieving an accuracy comparable to that of humans. Nonetheless, there are two issues that might hinder their a |
Subject: | Redes neurais convolucionais Aprendizado profundo Redes neurais (Computação) Reconhecimento facial (Computação) |
Country: | Reino Unido |
Editor: | Elsevier |
Citation: | Journal Of Visual Communication And Image Representation. ACADEMIC PRESS INC ELSEVIER SCIENCE, n. 36, p. 142 - 148. |
Rights: | fechado Aberto |
Identifier DOI: | 10.1016/j.jvcir.2015.12.015 |
Address: | https://www.sciencedirect.com/science/article/pii/S1047320315002552 |
Date Issue: | 2016 |
Appears in Collections: | IC - Artigos e Outros Documentos |
Files in This Item:
File | Size | Format | |
---|---|---|---|
000371280200012.pdf | 1.47 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.