Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2025, Vol. 19 Issue (3) : 193501    https://doi.org/10.1007/s11704-024-40465-z
Networks and Communication
DeepSwarm: towards swarm deep learning with bi-directional optimization of data acquisition and processing
Sicong LIU1, Bin GUO1(), Ziqi WANG1, Lehao WANG1, Zimu ZHOU2, Xiaochen LI1, Zhiwen YU1,3
1. School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an 710072, China
2. School of Data Science, City University of Hong Kong, Hong Kong 999077, China
3. College Of Computer Science And Technology, Harbin Engineering University, Harbin 150001, China
 Download: PDF(686 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Corresponding Author(s): Bin GUO   
Just Accepted Date: 19 July 2024   Issue Date: 19 September 2024
 Cite this article:   
Sicong LIU,Bin GUO,Ziqi WANG, et al. DeepSwarm: towards swarm deep learning with bi-directional optimization of data acquisition and processing[J]. Front. Comput. Sci., 2025, 19(3): 193501.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-40465-z
https://academic.hep.com.cn/fcs/EN/Y2025/V19/I3/193501
Fig.1  Comparison of Swarm DL and related concepts
Fig.2  Illustration of DeepSwarm, a generic system framework to realize bio-directional optimization of Swarm DL
Method Accuracy gain of global model Accuracy of mobile model after adaptation Accuracy gain of mobile model
IoU = 0.50 IoU = 0.50 IoU = 0.50
Mobile model A Mobile model B Mobile model C Average Mobile model A Mobile model B Mobile model C Average
Domain adaptation None 0.504 0.469 0.497 0.49 14.3% 48.9% 13.7% 23.4%
NestEvo without data generation 1.3% 0.504 0.475 0.501 0.505 14.3% 50.8% 15.5% 27.2%
Original mobile model None 0.441 0.315 0.437 0.397 None
Only mobile model adaptation 0 0.501 0.478 0.493 0.491 13.6% 51.7% 12.8% 23.7%
NestEvo 9.13% 0.571 0.543 0.584 0.566 29.5% 72.4% 33.6% 42.6%
Tab.1  Performance comparison of different DL model adaptation methods
1 S, Liu B, Guo C, Fang Z, Wang S, Luo Z, Zhou Z Yu . Enabling resource-efficient AIoT system with cross-level optimization: a survey. IEEE Communications Surveys & Tutorials, 2024, 26( 1): 389–427
2 S, Ma J, Pei W, Zhang G, Wang D, Feng F, Yu C, Song H, Qu C, Ma M, Lu F, Liu W, Zhou Y, Wu Y, Lin H, Li T, Wang J, Song X, Liu G, Li R, Zhao L Shi . Neuromorphic computing chip with spatiotemporal elasticity for multi-intelligent-tasking robots. Science Robotics, 2022, 7( 67): eabk2948
3 Y, Hu S, Fang Z, Lei Y, Zhang S Chen . Where2comm: communication-efficient collaborative perception via spatial confidence maps. In: Proceedings of the 36th Conference on Neural Information Processing Systems. 2022, 4874−4886
4 E, Bonabeau M, Dorigo G Theraulaz . Swarm Intelligence: from Natural to Artificial Systems. Oxford: Oxford University Press, 1999
5 R T, Mullapudi S, Chen K, Zhang D, Ramanan K Fatahalian . Online model distillation for efficient video inference. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. 2019. 3572−3581
6 Y, Chen W, Li C, Sakaridis D, Dai Gool L Van . Domain adaptive faster R-CNN for object detection in the wild. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018. 3339−3348
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed