Point-Based Multilevel Domain Adaptation for Point Cloud Segmentation
| Autor: | Xiaohuan Xi, Pu Wang, Hongwu Tan, Shuwen Peng, Cheng Wang, Rongchang Xie |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
business.industry
Computer science Intersection (set theory) Deep learning Point cloud Pattern recognition Geotechnical Engineering and Engineering Geology Image (mathematics) Domain (software engineering) Feature (computer vision) Point (geometry) Segmentation Artificial intelligence Electrical and Electronic Engineering business |
| Zdroj: | IEEE Geoscience and Remote Sensing Letters. 19:1-5 |
| ISSN: | 1558-0571 1545-598X |
| DOI: | 10.1109/lgrs.2020.3037702 |
| Popis: | Although good performance has been recently achieved in point cloud semantic segmentation based on deep learning, it has not been promoted due to differences in actual scenes and the time-consuming production of labeled data sets. Unsupervised domain adaptation (UDA) aims to solve the problem of how to adapt the classifier from one scene (source domain) to another unlabeled scene (target domain), which can reduce the performance drop caused by the domain shift. Since spatial information is important for light detection and ranging (LiDAR) point and the causes of domain gap in image and point cloud tasks are different, projecting point cloud into image for processing is not suitable and how to apply the image-oriented domain adaptation (DA) methods to point cloud is not trivial. In this letter, we propose a 3D point-based UDA method for point cloud semantic segmentation. This model introduces point- and set-level domain adaptive modules to achieve feature alignment between the domains. We evaluate the proposed method with two experiments, including cross terrain adaptation and airborne to mobile adaptation. Compared with the results without using DA, the mean intersection over union (mIoU) increased by 10.45% and 24.69%, respectively, indicating the effectiveness of our method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|