Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
4-2022
Abstract
While Deep Neural Network (DNN) models have transformed machine vision capabilities, their extremely high computational complexity and model sizes present a formidable deployment roadblock for AIoT applications. We show that the complexity-vs-accuracy-vs-communication tradeoffs for such DNN models can be significantly addressed via a novel, lightweight form of “collaborative machine intelligence” that requires only runtime changes to the inference process. In our proposed approach, called ComAI, the DNN pipelines of different vision sensors share intermediate processing state with one another, effectively providing hints about objects located within their mutually-overlapping Field-of-Views (FoVs). CoMAI uses two novel techniques: (a) a secondary shallow ML model that uses features from early layers of a peer DNN to predict object confidence values in the image, and (b) a pipelined sharing of such confidence values, by collaborators, that is then used to bias a reference DNN’s outputs. We demonstrate that CoMAI (a) can boost accuracy (recall) of DNN inference by 20-50%, (b) works across heterogeneous DNN models and deployments, and (c) incurs negligible processing, bandwidth and processing overheads compared to non-collaborative baselines.
Keywords
Deep learning, runtime, machine vision, neural networks
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
2022 IEEE International Conference on Computer Communications, Virtual Conference, May 2-5: Proceedings
First Page
41
Last Page
50
ISBN
9781665458221
Identifier
10.1109/INFOCOM48880.2022.9796769
Publisher
IEEE
City or Country
Piscataway, NJ
Embargo Period
5-23-2022
Citation
JAYARAJAH, Kasthuri; WANNIARACHCHIGE, Dhanuja; ABDELZAHER, Tarek; and MISRA, Archan.
ComAI: Enabling lightweight, collaborative intelligence by retrofitting vision DNNs. (2022). 2022 IEEE International Conference on Computer Communications, Virtual Conference, May 2-5: Proceedings. 41-50.
Available at: https://ink.library.smu.edu.sg/sis_research/7164
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/INFOCOM48880.2022.9796769
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons, Software Engineering Commons