An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
Kunran Xu, Huawei Zhang, Yishi Li, Yuhao Zhang, Rui Lai, Yi Liu

TL;DR
This paper introduces an ultra-low power TinyML system with a tiny CNN backbone, a neural co-processor, and a specialized instruction set, enabling real-time visual processing at the edge with minimal power consumption.
Contribution
It presents a novel TinyML system architecture combining a tiny CNN, a neural co-processor, and a custom instruction set for ultra-low power edge visual tasks.
Findings
Achieves 160mW power consumption for real-time object detection and recognition.
Demonstrates 30FPS processing speed on resource-constrained devices.
Maintains high accuracy with a compact model and specialized hardware.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCCD and CMOS Imaging Sensors · Advanced Neural Network Applications · Visual Attention and Saliency Detection
