Share Email Print

Proceedings Paper

Intermediate deep-feature compression for multitasking
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Collaborative intelligence is a new strategy to deploy deep neural network model for AI-based mobile devices, which runs a part of model on the mobile to extract features, the rest part in the cloud. In such case, feature data but not the raw image needs to be transmitted to cloud, and the features uploaded to cloud need have generalization capability to complete multitask. To this end, we design an encoder-decoder network to get intermediate deep features of image, and propose a method to make the features complete different tasks. Finally, we use a lossy compression method for intermediate deep features to improve transmission efficiency. Experimental results show that the features extracted by our network can complete input reconstruction and object detection simultaneously. Besides, with the deep-feature compression method proposed in our work, the quality of reconstructed image is good in visual and index of quantitative assessment, and object detection also has a good result in accuracy.

Paper Details

Date Published: 18 November 2019
PDF: 7 pages
Proc. SPIE 11187, Optoelectronic Imaging and Multimedia Technology VI, 111870Z (18 November 2019); doi: 10.1117/12.2538738
Show Author Affiliations
Weiqian Wang, Shanghai Univ. (China)
Ping An, Shanghai Univ. (China)
Chao Yang, Shanghai Univ. (China)
Xinpeng Huang, Shanghai Univ. (China)

Published in SPIE Proceedings Vol. 11187:
Optoelectronic Imaging and Multimedia Technology VI
Qionghai Dai; Tsutomu Shimura; Zhenrong Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?