Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows while preserving privacy and minimizing energy consumption. Deep Neural Networks (DNNs) have been shown to be well-suited to process these sensor data in an accurate and efficient manner. Nevertheless, the space of DNNs' architectures is huge and its manual exploration is burdensome and often leads to sub-optimal solutions. To overcome this problem, in this work, we propose a highly automated full-stack optimization flow for DNNs that goes from neural architecture search, mixed-precision quantization, and post-processing, down to the realization of a new smart sensor prototype, including a Microcontroller with a customized instruction set. Integrating these cross-layer optimizations, we obtain a large set of Pareto-optimal solutions in the 3D-space of energy, memory, and accuracy. Deploying such solutions on our hardware platform, we improve the state-of-the-art achieving up to 4.2x model size reduction, 23.8x code size reduction, and 15.38x energy reduction at iso-accuracy.
Weightless Neural Networks for Efficient Edge Inference
The University of Texas at Austin(德克萨斯大学奥斯汀分校);Federal University of Recôncavo da Bahia(巴伊亚州雷孔卡沃联邦大学);Federal University of Rio de Janeiro(里约热内卢联邦大学);Universidade Federal Fluminense(弗鲁米嫩塞联邦大学);ISCTE Instituto Universitario de Lisboa(里斯本大学学院)
Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University(迪肯大学智能系统研究与创新研究所);Cairo University(开罗大学);National University of Singapore(新加坡国立大学)
Label-Aware Ranked Loss for robust People Counting using Automotive in-cabin Radar
Infineon Technologies AG(英飞凌科技股份公司);Technical University of Munich(慕尼黑工业大学);Johannes Kepler University Linz(林茨约翰内斯·开普勒大学);Friedrich-Alexander-University Erlangen-Nuremberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学)
DeepCount: Crowd Counting with WiFi via Deep Learning
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Collaborative Innovation Center of Novel Software Technology and Industrialization(新型软件技术与产业化协同创新中心);Nantong University(南通大学)
Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
The Graduate Center of the City University of New York(纽约城市大学研究生中心);Borough of Manhattan Community College - CUNY(纽约城市大学曼哈顿社区学院);The City College of New York - CUNY(纽约城市大学纽约城市学院)
Crowd counting with crowd attention convolutional neural network
Institute of Intelligent Machines, Chinese Academy of Sciences(中国科学院智能机械研究所);University of Science and Technology of China(中国科学技术大学);Zhejiang Sci-Tech University(浙江理工大学)
Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
Nanyang Technological University(南洋理工大学);Huazhong University of Science and Technology(华中科技大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)