Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation

TL;DR

This paper introduces a novel unsupervised domain adaptation method for 3D point cloud classification that combines multimodal contrastive learning with optimal transport to improve domain alignment and class separation.

Contribution

It proposes a new architecture that integrates contrastive learning and optimal transport specifically tailored for 3D point cloud domain adaptation, achieving state-of-the-art results.

Findings

Achieves best performance on PointDA-10 dataset.

Significantly improves accuracy on GraspNetPC-10 with 4-12% margin.

Validates the effectiveness of contrastive learning and OT through ablation studies.

Abstract

Recently, the fundamental problem of unsupervised domain adaptation (UDA) on 3D point clouds has been motivated by a wide variety of applications in robotics, virtual reality, and scene understanding, to name a few. The point cloud data acquisition procedures manifest themselves as significant domain discrepancies and geometric variations among both similar and dissimilar classes. The standard domain adaptation methods developed for images do not directly translate to point cloud data because of their complex geometric nature. To address this challenge, we leverage the idea of multimodality and alignment between distributions. We propose a new UDA architecture for point cloud classification that benefits from multimodal contrastive learning to get better class separation in both domains individually. Further, the use of optimal transport (OT) aims at learning source and target data distributions jointly to reduce the cross-domain shift and provide a better alignment. We conduct a comprehensive empirical study on PointDA-10 and GraspNetPC-10 and show that our method achieves state-of-the-art performance on GraspNetPC-10 (with approx 4-12% margin) and best average performance on PointDA-10. Our ablation studies and decision boundary analysis also validate the significance of our contrastive learning module and OT alignment.