Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments
2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)(2021)
摘要
Deep neural networks provide high accuracy for perception. However they require high computational power. In particular, LiDAR-based object detection delivers good accuracy and real-time performance, but demands high computation due to expensive feature-extraction from point cloud data in the encoder and backbone networks. We investigate the model complexity versus accuracy trade-off using reinfor...
更多查看译文
关键词
Point cloud compression,Solid modeling,Three-dimensional displays,Conferences,Computational modeling,Object detection,Reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要