상세정보
학술대회
Practical Dense-to-Sparse Learning for a Manageable Object Detector on the Ground
- 발행일
- 202110
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1453-1455
- 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