Self-Ensemling for 3D Point Cloud Domain Adaption

by   Qing Li, et al.

Recently 3D point cloud learning has been a hot topic in computer vision and autonomous driving. Due to the fact that it is difficult to manually annotate a qualitative large-scale 3D point cloud dataset, unsupervised domain adaptation (UDA) is popular in 3D point cloud learning which aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain. However, the generalization and reconstruction errors caused by domain shift with simply-learned model are inevitable which substantially hinder the model's capability from learning good representations. To address these issues, we propose an end-to-end self-ensembling network (SEN) for 3D point cloud domain adaption tasks. Generally, our SEN resorts to the advantages of Mean Teacher and semi-supervised learning, and introduces a soft classification loss and a consistency loss, aiming to achieve consistent generalization and accurate reconstruction. In SEN, a student network is kept in a collaborative manner with supervised learning and self-supervised learning, and a teacher network conducts temporal consistency to learn useful representations and ensure the quality of point clouds reconstruction. Extensive experiments on several 3D point cloud UDA benchmarks show that our SEN outperforms the state-of-the-art methods on both classification and segmentation tasks. Moreover, further analysis demonstrates that our SEN also achieves better reconstruction results.


page 3

page 8


Self-Distillation for Unsupervised 3D Domain Adaptation

Point cloud classification is a popular task in 3D vision. However, prev...

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Deep neural networks have achieved promising performance in supervised p...

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

Deep-learning models for 3D point cloud semantic segmentation exhibit li...

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

Point cloud scene flow estimation is of practical importance for dynamic...

PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos

Self-supervised learning can extract representations of good quality fro...

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

Self-supervised learning has not been fully explored for point cloud ana...

Classifying In-Place Gestures with End-to-End Point Cloud Learning

Walking in place for moving through virtual environments has attracted n...

Please sign up or login with your details

Forgot password? Click here to reset