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

[61] Sigtia S, 2014, 2014 IEEE INT C AC S, P6959, DOI DOI 10.1109/ICASSP.2014.6854949
[62] Silfverberg M., 2000, CHI 2000 Conference Proceedings. Conference on Human Factors in Computing Systems. CHI 2000. The Future is Here, P9, DOI 10.1145/332040.332044
[63] Simonyan K, 2015, Arxiv, DOI arXiv:1409.1556
[64] Socher Richard, 2013, P 2013 C EMP METH NA, P1631, DOI DOI 10.1371/JOURNAL.PONE.0073791
[65] Song J, 2019, ISSCC DIG TECH PAP I, V62, P130, DOI 10.1109/ISSCC.2019.8662476
[66] Sutskever I, 2014, ADV NEUR IN, V27
[67] Rethinking the Inception Architecture for Computer Vision
Szegedy, Christian
Vanhoucke, Vincent
Ioffe, Sergey
Shlens, Jon
Wojna, Zbigniew
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 2818 - 2826
[68] Theocharous G., 2006, Intel Technology journal, V10, P299
[69] Synthetic Depth-of-Field with a Single-Camera Mobile Phone
Wadhwa, Neal
Garg, Rahul
Jacobs, David E.
Feldman, Bryan E.
Kanazawa, Nori
Carroll, Robert
Movshovitz-Attias, Yair
Barron, Jonathan T.
Pritch, Yael
Levoy, Marc
[J]. ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04):
[70] The Shazam music recognition service
Wang, Avery
[J]. COMMUNICATIONS OF THE ACM, 2006, 49 (08) : 44 - 48

← 1 2 3 4 5 6 7 8 →