DeepDecision: A Mobile Deep Learning Framework for Edge Video Analytics

By Xukan Ran, Haoliang Chen, Xiao-Dan Zhu, Zhenming Liu, Jiasi Chen. IEEE Conference on Computer Communications, 2018

430 citations recorded by the source corpus.

Deep learning shows great promise in providing more intelligence to augmented reality (AR) devices, but few AR apps use deep learning due to lack of infrastructure support. Deep learning algorithms are computationally intensive, and front-end devices cannot deliver sufficient compute power for real-time processing. In this work, we design a framework that ties together front-end devices with more powerful backend “helpers” (e.g., home servers) to allow deep learning to be executed locally or remotely in the cloud/edge. We consider the complex interaction between model accuracy, video quality, battery constraints, network data usage, and network conditions to determine an optimal offloading strategy. Our contributions are: (1) extensive measurements to understand the tradeoffs between video quality, network conditions, battery consumption, processing delay, and model accuracy; (2) a measurement-driven mathematical framework that efficiently solves the resulting combinatorial optimization problem; (3) an Android application that performs real-time object detection for AR applications, with experimental results that demonstrate the superiority of our approach.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7e739a65f5d5e8fa724322a832ef1de2aa614996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Xu Chen
2. Zhi Zhou
3. Liekang Zeng
4. Xiaofei Wang
5. Yiwen Han
6. Dusist Niyato
7. En Li
8. Junshan Zhang

In Computer Vision and Pattern Recognition

1. Xu Chen
2. Jiasi Chen
3. Xukan Ran
4. Liekang Zeng
5. Xiaofei Wang
6. Zhi Zhou
7. Yiwen Han
8. En Li

Citations in the corpus

• Deep Learning With Edge Computing: A Review (2019, methodology): “For example, even DNN models designed for mobile devices execute at 1–2 frames/s on modern smartphones [20], [78].”
• Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019, methodology): “DeepDecision [112] formulates the knob-tunning problem as a multiple-choice multiple-constraint knapsack program and solves it with an improved brute-force search method.”
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “In [172], the proposed distributed infrastructure DeepDecision ties together powerful edge nodes with less powerful end devices.”
• Deep Learning in Mobile and Wireless Networking: A Survey (2018, neutral): “[246] Object detection for AR applications.”
• Edge Assisted Real-time Object Detection for Mobile Augmented Reality (2019, background): “DeepDeci-sion [9] designs a framework to decide whether to offload the object detection task to the edge cloud or do local inference based on current network conditions.”
• Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics (2020, background): “DeepDecision [58] and MCDNN [34] treat resource scheduling as an optimization problem and maximize key metrics such as accuracy or latency, while LAVEA [78] allocates computation among multiple edge nodes, optimizing for latency.”
• All One Needs to Know about Fog Computing and Related Edge Computing Paradigms: A Complete Survey (2018, neutral): “Applications [20, 51, 61, 100, 154, 159, 174, 175, 190, 191, 247, 263, 271, 276, 287, 306, 320, 321, 323, 330–379]”