Xu, R., Lee, J., Wang, P., Bagchi, S., Li, Y., and Chaterji, S. (2022). LiteReconfig: cost and content aware reconfiguration of video object detection systems for mobile GPUs. Proceedings of the Seventeenth European Conference on Computer Systems, ACM-EuroSys 2022.
Paper BibTeX Alternative Link News Recording at ACM-EuroSys 2022
Students
Ran Xu, Jayoung Lee, Pengcheng Wang
Abstract
An adaptive video object detection system selects different
execution paths at runtime, based on video content and available
resources, so as to maximize accuracy under a target
latency objective (e.g., 30 frames per second). Such a system
is well suited to mobile devices with limited computing
resources, and often running multiple contending applications.
Existing solutions suffer from two major drawbacks.
First, collecting feature values to decide on an execution
branch is expensive. Second, there is a switching overhead
for transitioning between branches and this overhead depends
on the transition pair. LiteReconfig, an efficient and
adaptive video object detection framework, addresses these
challenges. LiteReconfig features a cost-benefit analyzer to
decide which features to use, and which execution branch
to run, at inference time. Furthermore, LiteReconfig has a
content-aware accuracy prediction model, to select an execution
branch tailored for frames in a video stream. We
demonstrate that LiteReconfig achieves significantly improved
accuracy under a set of varying latency objectives
than existing systems, while maintaining up to 50 fps on an
NVIDIA AGX Xavier board. Our code, with DOI, is available
at
https://doi.org/10.5281/zenodo.6345733.