Joint data and feature augmentation for self-supervised representation learning on point clouds
To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly produce sufficient transferability to high-level tasks on diffe...
| Главные авторы: | , , , |
|---|---|
| Формат: | Статья |
| Язык: | English |
| Опубликовано: |
Elsevier
2023-10-01
|
| Серии: | Graphical Models |
| Предметы: | |
| Online-ссылка: | http://www.sciencedirect.com/science/article/pii/S1524070323000188 |