HiRISE: High-Resolution Image Scaling for Edge ML via In-Sensor Compression and Selective ROI
Open Access
- 23 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Abstract
With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices. Recent works have achieved remarkable success in compressing ML models for object detection and image classification on microcontrollers with small memory, e.g., 512kB SRAM. However, there remain many challenges prohibiting the deployment of ML systems that require high-resolution images. Due to fundamental limits in memory capacity for tiny IoT devices, it may be physically impossible to store large images without external hardware. To this end, we propose a high-resolution image scaling system for edge ML, called HiRISE, which is equipped with selective region-of-interest (ROI) capability leveraging analog in-sensor image scaling. Our methodology not only significantly reduces the peak memory requirements, but also achieves up to 17.7× reduction in data transfer and energy consumption.Keywords
All Related Versions
Funding Information
- National Science Foundation (2340249, 2216773, 2216772, 2228028)
This publication has 9 references indexed in Scilit:
- Improving the Efficiency of CMOS Image Sensors through In-Sensor Selective Attention2023
- AdaFace: Quality Adaptive Margin for Face Recognition2022
- A Reconfigurable Convolution-in-Pixel CMOS Image Sensor ArchitectureIEEE Transactions on Circuits and Systems for Video Technology, 2022
- Senputing: An Ultra-Low-Power Always-On Vision Perception Chip Featuring the Deep Fusion of Sensing and ComputingIEEE Transactions on Circuits and Systems I: Regular Papers, 2021
- 7.7 A 0.2-to-3.6TOPS/W Programmable Convolutional Imager SoC with In-Sensor Current-Domain Ternary-Weighted MAC Operations for Feature Extraction and Region-of-Interest Detection2021
- MACSen: A Processing-In-Sensor Architecture Integrating MAC Operations Into Image Sensor for Ultra-Low-Power BNN-Based Intelligent Visual PerceptionIEEE Transactions on Circuits and Systems II: Express Briefs, 2020
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- A Low-Power Convolutional Neural Network Face Recognition Processor and a CIS Integrated With Always-on Face DetectorIEEE Journal of Solid-State Circuits, 2017
- Design of a 45nm 8-bit 2GS/s 250mW CMOS folding A/D converter with an adaptive digital error correction technique2015