Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper
This work addresses the challenge of efficiently deploying 3D scene understanding on mobile devices, offering an incremental improvement through automated parameter tuning.
The paper tackles the problem of optimizing algorithmic performance-accuracy trade-offs in 3D vision applications by using HyperMapper, a multi-objective Random Forest Active Learning framework, to automatically find good designs, resulting in speedups of 2 to over 12 on 83 smartphones and tablets compared to expert hand-tuning.
In this paper we investigate an emerging application, 3D scene understanding, likely to be significant in the mobile space in the near future. The goal of this exploration is to reduce execution time while meeting our quality of result objectives. In previous work we showed for the first time that it is possible to map this application to power constrained embedded systems, highlighting that decision choices made at the algorithmic design-level have the most impact. As the algorithmic design space is too large to be exhaustively evaluated, we use a previously introduced multi-objective Random Forest Active Learning prediction framework dubbed HyperMapper, to find good algorithmic designs. We show that HyperMapper generalizes on a recent cutting edge 3D scene understanding algorithm and on a modern GPU-based computer architecture. HyperMapper is able to beat an expert human hand-tuning the algorithmic parameters of the class of Computer Vision applications taken under consideration in this paper automatically. In addition, we use crowd-sourcing using a 3D scene understanding Android app to show that the Pareto front obtained on an embedded system can be used to accelerate the same application on all the 83 smart-phones and tablets crowd-sourced with speedups ranging from 2 to over 12.