Rate-energy-accuracy optimization of convolutional architectures for face recognition

Autor(es)

Bondi, L. ^[1] ; Baroffio, L. ^[1] ; Cesana, M. ^[1] ; Tagliasacchi, M. ^[1] ; Chiachia, G. ^[2] ; Rocha, A. ^[2]

Afiliação do(s) autor(es)

^[1] Politecn Milan, Dipartimento Elettron Informaz & Bioingg, Piazza Leonardo Da Vinci 32, I-20133 Milan - Italy

^[2] Univ Estadual Campinas, Inst Comp, Reasoning Complex Data RECOD Lab, UNICAMP, Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION; v. 36, p. 142-148, APR 2016.
• Citações Web of Science: 2

Resumo

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. (AU)

• Processo FAPESP: 13/11359-0 - Novos Métodos para Aprendizado de Hierarquias Visuais Profundas
• Beneficiário: Giovani Chiachia
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado