Proceedings ArticleDOI
Special Session: 2018 Low-Power Image Recognition Challenge and Beyond
Matthew Ardi,Alexander C. Berg,Bo Chen,Yen-Kuang Chen,Yi Chen,Dong-Hyun Kang,Jun-Hyeok Lee,Seungjae Lee,Yang Lu,Yung-Hsiang Lu,Fei Sun +10 more
- pp 154-157
TLDR
This paper summarizes LPIRC in year 2018 by describing the winners’ solutions and discusses the future of low-power computer vision.Abstract:
The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015. The competition identifies the best technologies that can detect objects in images efficiently (short execution time and low energy consumption). This paper summarizes LPIRC in year 2018 by describing the winners’ solutions. The paper also discusses the future of low-power computer vision.read more
References
More filters
Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Posted Content
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
TL;DR: This work proposes a small DNN architecture called SqueezeNet, which achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and is able to compress to less than 0.5MB (510x smaller than AlexNet).
Journal ArticleDOI
Some mathematical notes on three-mode factor analysis
TL;DR: The model for three-mode factor analysis is discussed in terms of newer applications of mathematical processes including a type of matrix process termed the Kronecker product and the definition of combination variables.
Proceedings ArticleDOI
Joint optimization of speed, accuracy, and energy for embedded image recognition systems
TL;DR: This paper presents the image recognition system that won the first prize in the LPIRC (Low Power Image Recognition Challenge) in 2017, and applied a series of software optimization techniques to improve throughput and explore the CPU and GPU frequencies to minimize the total energy consumption.
Related Papers (5)
The 1st Agriculture-Vision Challenge: Methods and Results
Mang Tik Chiu,Xingqian Xu,Kai Wang,Jennifer Hobbs,Naira Hovakimyan,Thomas S. Huang,Honghui Shi,Honghui Shi,Yunchao Wei,Zilong Huang,Alexander G. Schwing,Alexander G. Schwing,Robert J. Brunner,Ivan Dozier,Wyatt Dozier,Karen Ghandilyan,David Wilson,Hyunseong Park,Jun Hee Kim,Jun Hee Kim,Sungho Kim,Qinghui Liu,Michael Kampffmeyer,Robert Jenssen,Arnt-Børre Salberg,Alexandre Ormiga Galvão Barbosa,Rodrigo Trevisan,Bingchen Zhao,Shaozuo Yu,Siwei Yang,Yin Wang,Hao Sheng,Xiao Chen,Jingyi Su,Ram Rajagopal,Andrew Y. Ng,Van Thong Huynh,Soo-Hyung Kim,In Seop Na,Ujjwal Baid,Shubham Innani,Prasad Dutande,Bhakti Baheti,Sanjay N. Talbar,Jianyu Tang +44 more