Publications

Detailed Information

PointSplit: Towards On-device 3D Object Detection with Heterogeneous Low-power Accelerators

Cited 1 time in Web of Science Cited 1 time in Scopus
Authors

Park, Keondo; Choi, You Rim; Lee, Inhoe; Kim, Hyung-Sin

Issue Date
2023-05
Publisher
Association for Computing Machinery, Inc
Citation
IPSN 2023 - Proceedings of the 2023 22nd International Conference on Information Processing in Sensor Networks, pp.67-81
Abstract
Running deep learning models on resource-constrained edge devices has drawn significant attention due to its fast response, privacy preservation, and robust operation regardless of Internet connectivity. While these devices already cope with various intelligent tasks, the latest edge devices that are equipped with multiple types of low-power accelerators (i.e., both mobile GPU and NPU) can bring another opportunity; a task that used to be too heavy for an edge device in the single-accelerator world might become viable in the upcoming heterogeneous-accelerator world. To realize the potential in the context of 3D object detection, we identify several technical challenges and propose PointSplit, a novel 3D object detection framework for multi-accelerator edge devices that addresses the problems. Specifically, our PointSplit design includes (1) 2D semantics-aware biased point sampling, (2) parallelized 3D feature extraction, and (3) role-based group-wise quantization. We implement PointSplit on TensorFlow Lite and evaluate it on a customized hardware platform comprising both mobile GPU and EdgeTPU. Experimental results on representative RGB-D datasets, SUN RGB-D and Scannet V2, demonstrate that PointSplit on a multi-accelerator device is 24.7 × faster with similar accuracy compared to the full-precision, 2D-3D fusion-based 3D detector on a GPU-only device.
URI
https://hdl.handle.net/10371/202132
DOI
https://doi.org/10.1145/3583120.3587045
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • Graduate School of Data Science
Research Area Distributed machine learning, Edge, Mobile AI

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share