Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems
Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2X or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance.
Code (3)
Tasks
Birds Eye View Object DetectionCPUGPUObject DetectionSimilar Papers 제목 키워드 기반
SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements. PointPillars, a widely …
3D Object DetectionAutonomous DrivingObjectobject-detection+13DPillars: Pillar-based two-stage 3D object detection
PointPillars is the fastest 3D object detector that exploits pseudo image representations to encode features for 3D objects in a scene. Albeit efficient, PointPillars is typically outperformed by state-of-the-art 3D dete…
3D Object DetectionExploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs
The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix mul…
Skipping the Zeros in Diffusion Models for Sparse Data Generation
Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a signal. As a result, they erase sparsity pa…
SparseNN: An Energy-Efficient Neural Network Accelerator Exploiting Input and Output Sparsity
Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we le…
Efficient Neural Network