An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

Kavli Affiliate: Huawei Zhang

| First 5 Authors: Kunran Xu, Huawei Zhang, Yishi Li, Yuhao Zhang, Rui Lai

| Summary:

Tiny machine learning (TinyML), executing AI workloads on resource and power
strictly restricted systems, is an important and challenging topic. This brief
firstly presents an extremely tiny backbone to construct high efficiency CNN
models for various visual tasks. Then, a specially designed neural co-processor
(NCP) is interconnected with MCU to build an ultra-low power TinyML system,
which stores all features and weights on chip and completely removes both of
latency and power consumption in off-chip memory access. Furthermore, an
application specific instruction-set is further presented for realizing agile
development and rapid deployment. Extensive experiments demonstrate that the
proposed TinyML system based on our model, NCP and instruction set yields
considerable accuracy and achieves a record ultra-low power of 160mW while
implementing object detection and recognition at 30FPS. The demo video is
available on url{https://www.youtube.com/watch?v=mIZPxtJ-9EY}.

| Search Query: ArXiv Query: search_query=au:”Huawei Zhang”&id_list=&start=0&max_results=10

Read More