Abstract
In the field of computer vision technology, deep learning of image processing has become an emerging research area. The semantic segmentation of an image is among the utmost essential and significant tasks in image-processing research, offering a wide range of application fields such as autonomous driving systems, medical diagnosis, surveillance security, etc. Thus far, many studies have suggested and developed neural network modules in deep learning. To the best of our knowledge, all existing neural networks for semantic segmentation have large parameter sizes and it is therefore unfeasible to implement those architectures in low-power and memory-limited embedded platforms such as FPGAs. Building an embedded platform with that architecture is possible after reducing the parameter size without affecting the module’s architecture. The quantization technique lowers the precision of the neural network parameters while mostly keeping the accuracy. In this paper, we propose a quantization algorithm for a semantic segmentation deep learning architecture, which reduces the parameter size by four to eight times with a negligible accuracy abatement. As long as the parameter size is reduced, the deep learning architecture is improved in terms of required storage, computational speed, and power efficiency.
Funder
Ministry of Science and Technology of Taiwan
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference55 articles.
1. Image segmentation using K-means clustering algorithm and subtractive clustering algorithm;Dhanachandra;Procedia Comput. Sci.,2015
2. Plath, N., Toussaint, M., and Nakajima, S. Multi-class image segmentation using conditional random fields and global classification. Proceedings of the 26th Annual International Conference on Machine Learning.
3. Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., and Cottrell, G. Understanding convolution for semantic segmentation. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).
4. Shotton, J., Johnson, M., and Cipolla, R. Semantic texton forests for image categorization and segmentation. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition.
5. Schroff, F., Criminisi, A., and Zisserman, A. Object Class Segmentation using Random Forests. Proceedings of the BMVC.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献