Graph Attentive Dual Ensemble learning for Unsupervised Domain Adaptation on point clouds

Qing Li, Chuan Yan, Qi Hao, Xiaojiang Peng, Li Liu

Abstract: Highlights•We propose Graph Attentive Dual Ensemble (GRADE) for efficient semantic transfer in 3D point clouds.•We propose a dual ensemble network for consistent generalization and accurate reconstruction.•We propose a dynamic graph attentive module to enhance semantic features in 3D point clouds.•We propose an intra-domain mixup scheme to increase training sample diversity.•Experiments show GRADE achieves SOTA performance on 3D point cloud classification and segmentation.