A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions

arXiv:2403.07542v1 Announce Type: cross
Abstract: This survey explores the adaptation of visual transformer models in Autonomous Driving, a transition inspired by their success in Natural Language Processing. Surpassing traditional Recurrent Neural Networks in tasks like sequential image processing and outperforming Convolutional Neural Networks in global context capture, as evidenced in complex scene recognition, Transformers are gaining traction in computer vision. These capabilities are crucial in Autonomous Driving for real-time, dynamic visual scene processing. Our survey provides a comprehensive overview of …

abstract arxiv autonomous autonomous driving context convolutional neural networks cs.cv cs.lg current driving future global image image processing language language processing natural natural language natural language processing networks neural networks processing recurrent neural networks success survey tasks transformer transformer models transformers transition trends type vision vision transformers visual