Mengye Ren, Andrei Pokrovsky, Bin Yang, Raquel Urtasun
TL;DR本文介绍了一种新型的基于拼贴的稀疏卷积算法,通过利用计算掩码的稀疏结构,降低了 CNN 中高分辨率计算的复杂度,并应用于基于 LiDAR 的 3D 目标检测中,最终获得了显著的速度提升而无需牺牲准确率。
Abstract
Conventional deep convolutional neural networks (CNNs) apply convolution
operators uniformly in space across all feature maps for hundreds of layers -
this incurs a high computational cost for real-time applications. For many
problems such as object detection and semantic segmentation,