HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要