Low-Power Computer Vision

George K. Thiruvathukal is a professor of Computer Science at Loyola University Chicago, Illinois, USA. He is also a visiting faculty at Argonne National Laboratory. His research areas include high performance and distributed computing, softwareengineering, and programming languages.Yung-Hsiang Lu is a professor of Electrical and Computer Engineering at Purdue University, Indiana, USA. He is the first director of Purdue’s John Martinson Engineering Entrepreneurial Center. He is a fellow of the IEEE and distinguished scientist of the ACM. His research interests include computer vision, mobile systems, and cloud computing.Jaeyoun Kim is a technical program manager at Google, California, USA. He leads AI research projects, including MobileNets and TensorFlow Model Garden, to build state-of-the-art machine learning models and modeling libraries for computer vision and natural language processing.Yiran Chen is a professor of Electrical and Computer Engineering at Duke University, North Carolina, USA. He is a fellow of the ACM and the IEEE. His research areas include new memory and storage systems, machine learning and neuromorphiccomputing, and mobile computing systems.Bo Chen is the Director of AutoML at DJI, Guangdong, China. Before joining DJI, he was a researcher at Google, California, USA. His research interests are the optimization of neural network software and hardware as well as landing AI technology in products with stringent resource constraints.

On device AI has become increasingly important for reasons of latency, privacy and overall autonomy as computing becomes more and more ambient. Moreover, making AI, in particular computer vision, efficient and run well in low resource computing environments using frameworks like PyTorch is a priority of the industry to enable this. The IEEE Low-Power Computer Vision Challenge is one such effort that has and continues to push the field forward allowing us to make progress in this area. Facebook has been a proud sponsor and supporter of this challenge since 2018 and this book presents the winners’ solutions from previous challenges and can guide researchers, engineers, and students to design efficient on device AI.-- Joe Spisak, Product Lead at Facebook Artificial IntelligenceComputer vision is at the center of recent breakthroughs in artificial intelligence. Being able to process visual data in low-power computing environments will enable great advances in the field in areas such as edge computing and Internet of Things. This book presents work by experts in the field and their winning solutions. It is an indispensable resource for anyone interested creating AI technologies in resource constrained computing environments-- Mark Liao, Director, Institute of Information Science, Academia SinicaFrom mobile phones to wearable health monitors, improved energy efficiency is the enabling technology of everything we take for granted today. Computer vision is at the center of artificial intelligence and machine learning. Today, artificial intelligence and low power are often at different ends of the spectrum. Low-power computer vision will enable greater adoption of the technologies in battery-powered IoT (Internet of Things) systems. This book collects the winners’ solutions of the Low-Power Computer Vision Challenge and provides insight on how to improve efficiency of artificial intelligence.-- Edwin Park, Principal Engineer at Qualcomm

• Section I IntroductionBook Introduction Yung-Hsiang Lu, George K. Thiruvathukal, Jaeyoun Kim, Yiran Chen, and Bo ChenHistory of Low-Power Computer Vision Challenge Yung-Hsiang Lu and Xiao Hu, Yiran Chen, Joe Spisak, Gaurav Aggarwal, Mike Zheng Shou, and George K. ThiruvathukalSurvey on Energy-Efficient Deep Neural Networks for Computer Vision Abhinav Goel, Caleb Tung, Xiao Hu, Haobo Wang, and Yung-Hsiang Lu and George K. ThiruvathukalSection II Competition WinnersHardware design and software practices for efficient neural network inference Yu Wang, Xuefei Ning, Shulin Zeng, Yi Kai, Kaiyuan Guo, and Hanbo Sun, Changcheng Tang, Tianyi Lu, Shuang Liang, and Tianchen ZhaoProgressive Automatic Design of Search Space for One-Shot Neural Architecture SearchXin Xia, Xuefeng Xiao, and Xing WangFast Adjustable Threshold For Uniform Neural Network QuantizationAlexander Goncharenko, Andrey Denisov, and Sergey AlyamkinPower-efficient Neural Network Scheduling on Heterogeneous SoCsYing Wang, Xuyi Cai, and Xiandong ZhaoEfficient Neural Network ArchitecturesHan Cai and Song HanDesign Methodology for Low Power Image Recognition SystemsSoonhoi Ha, EunJin Jeong, Duseok Kang, Jangryul Kim, and Donghyun KangGuided Design for Efficient On-device Object Detection ModelTao Sheng and Yang LiuSection III Invited ArticlesQuantizing Neural Networks Marios Fournarakis, Markus Nagel, Rana Ali Amjad, Yelysei Bondarenko, Mart van Baalen, and Tijmen BlankevoortA practical guide to designing efficient mobile architecturesMark Sandler and Andrew HowardA Survey of Quantization Methods for Efficient Neural Network InferenceAmir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael Mahoney, and Kurt KeutzerBibliographyIndex