ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 A Method of Deep Learning Model Optimization for Image Classification on Edge Device
Cited 3 time in scopus Download 115 time Share share facebook twitter linkedin kakaostory
저자
이형극, 이남경, 이성진
발행일
202210
출처
Sensors, v.22 no.19, pp.1-15
ISSN
1424-8220
출판사
MDPI
DOI
https://dx.doi.org/10.3390/s22197344
협약과제
22HH5100, 지능적 미디어 속성 추출 및 공유 기술 개발, 이남경
초록
Due to the recent increasing utilization of deep learning models on edge devices, the industry demand for Deep Learning Model Optimization (DLMO) is also increasing. This paper derives a usage strategy of DLMO based on the performance evaluation through light convolution, quantization, pruning techniques and knowledge distillation, known to be excellent in reducing memory size and operation delay with a minimal accuracy drop. Through experiments regarding image classification, we derive possible and optimal strategies to apply deep learning into Internet of Things (IoT) or tiny embedded devices. In particular, strategies for DLMO technology most suitable for each on-device Artificial Intelligence (AI) service are proposed in terms of performance factors. In this paper, we suggest a possible solution of the most rational algorithm under very limited resource environments by utilizing mature deep learning methodologies.
KSP 제안 키워드
AND operation, Edge devices, Embedded Devices, Image classification, Internet of thing(IoT), Memory size, Model optimization, Performance evaluation, Performance factors, Pruning techniques, artificial intelligence
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)