A 49.5 mW Multi-Scale Linear Quantized Online Learning Processor for Real-Time Adaptive Object Detection

Online training is essential to maintain a high object detection (OD) in various environments. However, additional computation workload, EMA, and high bit precision is the problem of conventional online learning scheme on mobile devices. Therefore, a low power real-time online learning OD processor...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems. II, Express briefs Express briefs, 2022-05, Vol.69 (5), p.2443-2447
Main Authors: Song, Seokchan, Kim, Soyeon, Park, Gwangtae, Han, Donghyeon, Yoo, Hoi-Jun
Format: Article
Language:English
Subjects:
Adaptation models
Computation
Datasets
Degradation
Distance learning
Electronic devices
Estimation
Low-power accelerator
Machine learning
Microprocessors
multi-scale linear quantization (MSLQ)
Object detection
Object recognition
Online instruction
online learning processor
Power consumption
Power management
Quantization (signal)
Real time
Real-time systems
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Online training is essential to maintain a high object detection (OD) in various environments. However, additional computation workload, EMA, and high bit precision is the problem of conventional online learning scheme on mobile devices. Therefore, a low power real-time online learning OD processor is proposed with three key features. First, multi-scale linear quantization (MSLQ) and MSLQ-aware PE structure are proposed for low-bit computation. Second, channel-wise gradient skipping is proposed to reduce computation and EMA based on temporal correlation. These schemes reduce ~56% of computation burden and ~30% of EMA, and also improve detection accuracy. Lastly, gradient norm clipping with norm estimation achieves 3.8 mAP improvement at YouTube-Objects dataset by fast adaptation with under 1% of the additional computation. Finally, the proposed online learning OD processor is implemented in 28 nm CMOS technology and occupies 1.2 mm 2 . The proposed processor achieves 78 mAP of detection accuracy at the YouTube-Objects dataset. Compared to the previous OD processor, this brief shows state-of-the-art performance by achieving 49.5 mW power consumption and 34.4 frame-per-second real-time online learning OD on mobile devices.
ISSN:1549-7747
1558-3791
DOI:10.1109/TCSII.2022.3160160