ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Practical Dense-to-Sparse Learning for a Manageable Object Detector on the Ground
Cited 0 time in scopus Download 4 time Share share facebook twitter linkedin kakaostory
저자
문용혁, 이용주
발행일
202110
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1453-1455
DOI
https://dx.doi.org/10.1109/ICTC52510.2021.9620843
협약과제
21HS7200, 능동적 즉시 대응 및 빠른 학습이 가능한 적응형 경량 엣지 연동분석 기술개발, 문용혁
초록
This paper presents how to construct a manageable neural network in terms of architecture and parameters with less accuracy loss to guarantee feasible model deployment on small footprint devices. We thus propose a practical dense-to-sparse learning method of using architecture rescaling and channel sparsification. From a dense detector with 7.2M parameters, we achieve promising sparse models with a compression rate of 81x-300x and an accuracy drop of 5.03%-21.26%. Our experimental result shows a high possibility of producing various variants of sparse networks for object detection.
KSP 제안 키워드
Accuracy loss, Compression rate, Experimental Result, Learning methods, Model deployment, Object detection, Sparse model, Sparse networks, neural network, object detector, small footprint