Joint data and feature augmentation for self-supervised representation learning on point clouds

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...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: Zhuheng Lu, Yuewei Dai, Weiqing Li, Zhiyong Su
Aineistotyyppi: Artikkeli
Kieli:English
Julkaistu: Elsevier 2023-10-01
Sarja:Graphical Models
Aiheet:
Contrastive learning
Self-supervised learning
Point cloud
Representation learning
Linkit:http://www.sciencedirect.com/science/article/pii/S1524070323000188

Internet

http://www.sciencedirect.com/science/article/pii/S1524070323000188

Samankaltaisia teoksia