MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning
This work addresses multi-task learning for visual perception in autonomous driving, offering incremental improvements by leveraging temporal information and a novel loss strategy.
The authors tackled the problem of multi-task learning in autonomous driving by proposing a multi-stream network that processes sequences of images and a geometric mean loss function, achieving improved performance on KITTI, Cityscapes, and SYNTHIA datasets compared to existing methods.
Multi-task learning is commonly used in autonomous driving for solving various visual perception tasks. It offers significant benefits in terms of both performance and computational complexity. Current work on multi-task learning networks focus on processing a single input image and there is no known implementation of multi-task learning handling a sequence of images. In this work, we propose a multi-stream multi-task network to take advantage of using feature representations from preceding frames in a video sequence for joint learning of segmentation, depth, and motion. The weights of the current and previous encoder are shared so that features computed in the previous frame can be leveraged without additional computation. In addition, we propose to use the geometric mean of task losses as a better alternative to the weighted average of task losses. The proposed loss function facilitates better handling of the difference in convergence rates of different tasks. Experimental results on KITTI, Cityscapes and SYNTHIA datasets demonstrate that the proposed strategies outperform various existing multi-task learning solutions.