BROWSE
Detail
Conference Paper
Practical Dense-to-Sparse Learning for a Manageable Object Detector on the Ground
Cited 0 time in 
Share 
Share
- Authors
- Yong-Hyuk Moon, Yong-Ju Lee
- Issue Date
- 2021-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1453-1455
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- 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 Keywords
- Accuracy loss, Compression rate, Experimental Result, Learning methods, Model deployment, Sparse model, Sparse networks, neural network(NN), object detection, object detector, small footprint