Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

Abstract-- Bird's Eye View (BEV) is a popular representation Our main contributions include: 1) A new pipeline that maintains and exploits representational I. In the autonomous vehicle space, high-end desktop same power budget or modest runtime speedups for GPUs and CPUs are often available on-board, but this a significantly smaller power budget, all in exchange hardware still faces power and cost limits and must be for a modest decrease in detection quality. This 3) A general design approach centered around representational challenge is even more pronounced for intelligent mobile sparsity for efficient embedded system pipelines. GPUs and high-end CPUs in order to run its control stack. One generalpurpose the problem of developing machine learning models that have solution to this problem, model quantization [5]-[9], significantly reduced resource usage compared to existing first trains models in a standard fashion using floating point models while preserving their performance -- models need weights and then, after training, converts some [5] or all [6], to be shrunk not just to fit on smaller devices, but to fit while [7] weights into integer [8] or binary [9] quantized values that sharing these resources with other components.