This paper presents an in-depth analysis of the majority of the deep neural networks (DNNs) proposed in the state of the art for image recognition. For each DNN, multiple performance indices are observed, such as recognition accuracy, model complexity, computational complexity, memory usage, and inference time. The behavior of such performance indices and some combinations of them are analyzed and discussed. To measure the indices, we experiment the use of DNNs on two different computer architectures, a workstation equipped with a NVIDIA Titan X Pascal, and an embedded system based on a NVIDIA Jetson TX1 board. This experimentation allows a direct comparison between DNNs running on machines with very different computational capacities. This paper is useful for researchers to have a complete view of what solutions have been explored so far and in which research directions are worth exploring in the future, and for practitioners to select the DNN architecture(s) that better fit the resource constraints of practical deployments and applications. To complete this work, all the DNNs, as well as the software used for the analysis, are available online.

Bianco, S., Cadene, R., Celona, L., Napoletano, P. (2018). Benchmark analysis of representative deep neural network architectures. IEEE ACCESS, 6, 64270-64277 [10.1109/ACCESS.2018.2877890].

Benchmark analysis of representative deep neural network architectures

Bianco, S;Celona, L
;
Napoletano, P
2018

Abstract

This paper presents an in-depth analysis of the majority of the deep neural networks (DNNs) proposed in the state of the art for image recognition. For each DNN, multiple performance indices are observed, such as recognition accuracy, model complexity, computational complexity, memory usage, and inference time. The behavior of such performance indices and some combinations of them are analyzed and discussed. To measure the indices, we experiment the use of DNNs on two different computer architectures, a workstation equipped with a NVIDIA Titan X Pascal, and an embedded system based on a NVIDIA Jetson TX1 board. This experimentation allows a direct comparison between DNNs running on machines with very different computational capacities. This paper is useful for researchers to have a complete view of what solutions have been explored so far and in which research directions are worth exploring in the future, and for practitioners to select the DNN architecture(s) that better fit the resource constraints of practical deployments and applications. To complete this work, all the DNNs, as well as the software used for the analysis, are available online.
Articolo in rivista - Articolo scientifico
Convolutional neural networks; Deep neural networks; Image recognition;
Computational complexity; Computational modeling; Convolutional neural networks; Deep neural networks; Embedded systems; Graphics processing units; Image recognition; Memory management; Computer Science (all); Materials Science (all); Engineering (all)
English
2018
6
64270
64277
8506339
partially_open
Bianco, S., Cadene, R., Celona, L., Napoletano, P. (2018). Benchmark analysis of representative deep neural network architectures. IEEE ACCESS, 6, 64270-64277 [10.1109/ACCESS.2018.2877890].
File in questo prodotto:
File Dimensione Formato  
benchmark_access_2018.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 9.8 MB
Formato Adobe PDF
9.8 MB Adobe PDF Visualizza/Apri
benchmark.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 9.8 MB
Formato Adobe PDF
9.8 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/209843
Citazioni
  • Scopus 550
  • ???jsp.display-item.citation.isi??? 447
Social impact