AI Benchmark: All About Deep Learning on Smartphones in 2019

被引：106

作者：

Ignatov, Andrey ^{[1
]}

Timofte, Radu ^{[1
]}

Kulik, Andrei ^{[2
]}

Yang, Seungsoo ^{[3
]}

Wang, Ke ^{[4
]}

Baum, Felix ^{[5
]}

Wu, Max ^{[6
]}

Xu, Lirong ^{[7
]}

Van Gool, Luc ^{[1
]}

机构：

[1] Swiss Fed Inst Technol, Zurich, Switzerland

[2] Google Res, Zurich, Switzerland

[3] Samsung Inc, Seoul, South Korea

[4] Huawei Inc, Shenzhen, Peoples R China

[5] Qualcomm Inc, San Diego, CA USA

[6] MediaTek Inc, Hsinchu, Taiwan

[7] Unisoc Inc, Shanghai, Peoples R China

来源：

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2019年

关键词：

RECOGNITION; PHONE;

D O I：

10.1109/ICCVW.2019.00447

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The performance of mobile AI accelerators has been evolving rapidly in the past two years, nearly doubling with each new generation of SoCs. The current 4th generation of mobile NPUs is already approaching the results of CUDA-compatible Nvidia graphics cards presented not long ago, which together with the increased capabilities of mobile deep learning frameworks makes it possible to run complex and deep AI models on mobile devices. In this paper, we evaluate the performance and compare the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference. We also discuss the recent changes in the Android ML pipeline and provide an overview of the deployment of deep learning models on mobile devices. All numerical results provided in this paper can be found and are regularly updated on the official project website(1).

引用

页码：3617 / 3635

页数：19

共 72 条

[31] Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, Benoit
Kligys, Skirmantas
Chen, Bo
Zhu, Menglong
Tang, Matthew
Howard, Andrew
Adam, Hartwig
Kalenichenko, Dmitry
[J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2704 - 2713
[32] Kim J, 2016, PROC CVPR IEEE, P1637, DOI [10.1109/CVPR.2016.181, 10.1109/CVPR.2016.182]
[33] Camera-based Kanji OCR for mobile-phones: Practical issues
Koga, M
Mine, R
Kameyama, T
Takahashi, T
Yamazaki, M
Yamaguchi, T
[J]. EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 635 - 639
[34] Krishnamoorthi R., 2018, ARXIV180608342
[35] ImageNet Classification with Deep Convolutional Neural Networks
Krizhevsky, Alex
Sutskever, Ilya
Hinton, Geoffrey E.
[J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90
[36] Kwapisz J.R., 2011, ACM SIGKDD Explorations Newsl, V12, P74, DOI [DOI 10.1145/1964897.1964918, 10.1145/1964897.1964918]
[37] Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y.
Boser, B.
Denker, J. S.
Henderson, D.
Howard, R. E.
Hubbard, W.
Jackel, L. D.
[J]. NEURAL COMPUTATION, 1989, 1 (04) : 541 - 551
[38] Gradient-based learning applied to document recognition
Lecun, Y
Bottou, L
Bengio, Y
Haffner, P
[J]. PROCEEDINGS OF THE IEEE, 1998, 86 (11) : 2278 - 2324
[39] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, Christian
Theis, Lucas
Huszar, Ferenc
Caballero, Jose
Cunningham, Andrew
Acosta, Alejandro
Aitken, Andrew
Tejani, Alykhan
Totz, Johannes
Wang, Zehan
Shi, Wenzhe
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 105 - 114
[40] Lee Juhyun, 2019, ARXIV190701989

← 1 2 3 4 5 6 7 8 →