A Survey on Deep Domain Adaptation for LiDAR Perception
arXiv:2106.02377 · doi:10.1109/IVWorkshops54471.2021.9669228
Abstract
Scalable systems for automated driving have to reliably cope with an open-world setting. This means, the perception systems are exposed to drastic domain shifts, like changes in weather conditions, time-dependent aspects, or geographic regions. Covering all domains with annotated data is impossible because of the endless variations of domains and the time-consuming and expensive annotation process. Furthermore, fast development cycles of the system additionally introduce hardware changes, such as sensor types and vehicle setups, and the required knowledge transfer from simulation. To enable scalable automated driving, it is therefore crucial to address these domain shifts in a robust and efficient manner. Over the last years, a vast amount of different domain adaptation techniques evolved. There already exists a number of survey papers for domain adaptation on camera images, however, a survey for LiDAR perception is absent. Nevertheless, LiDAR is a vital sensor for automated driving that provides detailed 3D scans of the vehicle's surroundings. To stimulate future research, this paper presents a comprehensive review of recent progress in domain adaptation methods and formulates interesting research questions specifically targeted towards LiDAR perception.
Accepted at IEEE Intelligent Vehicles Symposium (IV) 2021 Workshop on Autonomy at Scale. 8 pages, 5 figures
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Conditional Generative Adversarial Nets
- Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems
- CNN-based Lidar Point Cloud De-Noising in Adverse Weather
- PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
- Progressive Graph Learning for Open-Set Domain Adaptation
- LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving
- Unsupervised Domain Adaptation in Semantic Segmentation: a Review
- Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation
- Pseudo-labeling for Scalable 3D Object Detection