计算机科学
人工智能
特征(语言学)
特征学习
任务(项目管理)
利用
块(置换群论)
图形
模式识别(心理学)
机器学习
理论计算机科学
管理
数学
几何学
哲学
语言学
计算机安全
经济
出处
期刊:
[Association for Computing Machinery]
日期:2023-10-26
卷期号:: 800-808
被引量:1
标识
DOI:10.1145/3581783.3612021
摘要
Efficient and accurate perception system is critical for autonomous driving, including traffic object detection, drivable area segmentation, and lane detection. Most previous works do not consider the spatial and semantic cues in traffic scenes. In this paper, we propose a novel multi-task learning network to exploit these priors. Specifically, to model the co-occurrence and spatial relationships of traffic objects, we propose to use a Graph Convolutional Network (GCN) block operating on the patches of feature maps. It enables adaptive discovery and incorporation of semantic and spatial relationships in the feature space. Furthermore, we propose a sub-feature sharing method to mitigate negative transfer in multi-task learning. On the basis of a fully shared base network, we split the feature space of different tasks along the channel dimension, resulting in the shared and private features for each task. It allows the network parameters to be selectively updated by different tasks during training. Experimental results on the challenging BDD100K dataset demonstrate that our proposed approach gets consistent improvement with fewer parameters, and achieves new state-of-the-art performance in terms of accuracy and speed.
科研通智能强力驱动
Strongly Powered by AbleSci AI