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...
| Autori principali: | , , , |
|---|---|
| Natura: | Articolo |
| Lingua: | English |
| Pubblicazione: |
Elsevier
2023-10-01
|
| Serie: | Graphical Models |
| Soggetti: | |
| Accesso online: | http://www.sciencedirect.com/science/article/pii/S1524070323000188 |