SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data

no code implementations • 13 Jan 2022 • Xingye Li, Ling Zhang, Zhigang Zhu

To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works on the unlabeled point cloud data of a complex 3D scene.

Contrastive Learning Self-Supervised Learning +2