MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving 论文

2018引用 689

Advanced Neural Network ApplicationsMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot Learning

人工智能 Advanced Neural Network Applications Domain Adaptation and Few-Shot Learning Multimodal Machine Learning Applications

关系图谱

作者

摘要

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation using a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second. Training scripts and trained weights to reproduce our results can be found here: https://github.com/MarvinTeichmann/MultiNet

作者查看全部 (5)

Raquel Urtasun

Roberto Cipolla

Marius Zöllner

Michael Weber

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving 论文

详细信息

摘要

作者查看全部 (5)

相关技术查看全部 (3)

相关事件

相关文章