MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
This work addresses the need for efficient, real-time perception in autonomous driving systems, representing an incremental improvement in multi-task learning for this domain.
The paper tackles the problem of enabling real-time semantic reasoning for autonomous driving by proposing a unified architecture for joint classification, detection, and segmentation, achieving state-of-the-art performance in road segmentation on the KITTI dataset with processing times under 100 ms.
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 via 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, outperforming the state-of-the-art in the road segmentation task. Our approach is also very efficient, taking less than 100 ms to perform all tasks.