Self-Supervised Learning for Domain Adaptation on Point-Clouds

2020/03/29 by Idan Achituve, Achituve, Idan, Haggai Maron +3 · 6 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Human Pose and Action Recognition #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2003.12641

openalex publication_date 2020/03/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and videos. It is still unknown if and how it can be leveraged for domain adaptation in 3D perception problems. Here we describe the first study of SSL for DA on point clouds. We introduce a new family of pretext tasks, Deformation Reconstruction, inspired by the deformations encountered in sim-to-real transformations. In addition, we propose a novel training procedure for labeled point cloud data motivated by the MixUp method called Point cloud Mixup (PCM). Evaluations on domain adaptations datasets for classification and segmentation, demonstrate a large improvement over existing and baseline methods.

Citations

• Deep Domain Confusion: Maximizing for Domain Invariance
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ShapeNet: An Information-Rich 3D Model Repository
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• Deep Learning for 3D Point Clouds: A Survey

Cited by

• CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images
• NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
• Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
• LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstruction
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

Related

• Self-Ensemling for 3D Point Cloud Domain Adaption
• Self-Distillation for Unsupervised 3D Domain Adaptation
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation
• Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation