https://scholars.lib.ntu.edu.tw/handle/123456789/634331
標題: | 3D-SELFCUTMIX: SELF-SUPERVISED LEARNING FOR 3D POINT CLOUD ANALYSIS | 作者: | Xu, Yuan Yi Ji, Yan Yang Huang, Sheng Yu Lin, Zhi Hao YU-CHIANG WANG |
關鍵字: | classification | point cloud analysis | Self-supervised learning | 公開日期: | 1-一月-2022 | 來源出版物: | Proceedings - International Conference on Image Processing, ICIP | 摘要: | Point clouds have been widely applied to represent 3D data, with a variety of applications such as autonomous driving, augmented reality, and robotics. Since collecting a large amount of labeled 3D point cloud data for training deep learning models might not always be applicable, we propose the novel learning strategy of 3D-SelfCutMix, which advances mixed-sample data augmentation techniques while exploiting the spatial and semantic consistencies between point cloud data. Depending on the availability of label supervision, the proposed network can be realized in either self-supervised or fully-supervised manners, while both versions are shown to benefit downstream tasks. In our experiments, we consider a variety of tasks including classification and part-segmentation tasks, which sufficiently support the use of the proposed method for 3D point cloud analysis. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/634331 | ISBN: | 9781665496209 | ISSN: | 15224880 | DOI: | 10.1109/ICIP46576.2022.9897785 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。