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...
| 主要な著者: | , , , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
Elsevier
2023-10-01
|
| シリーズ: | Graphical Models |
| 主題: | |
| オンライン･アクセス: | http://www.sciencedirect.com/science/article/pii/S1524070323000188 |