Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting
Learning from unlabeled or partially labeled data to alleviate human labeling remains a challenging research topic in 3D modeling. Along this line, unsupervised representation learning is a promising direction to auto-extract features without human intervention. This paper proposes a general unsupervised approach, named \textbf{ConClu}, to perform the learning of point-wise and global features by jointly leveraging point-level clustering and instance-level contrasting. Specifically, for one thing, we design an Expectation-Maximization (EM) like soft clustering algorithm that provides local supervision to extract discriminating local features based on optimal transport. We show that this criterion extends standard cross-entropy minimization to an optimal transport problem, which we solve efficiently using a fast variant of the Sinkhorn-Knopp algorithm. For another, we provide an instance-level contrasting method to learn the global geometry, which is formulated by maximizing the similarity between two augmentations of one point cloud. Experimental evaluations on downstream applications such as 3D object classification and semantic segmentation demonstrate the effectiveness of our framework and show that it can outperform state-of-the-art techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object ClassificationClusteringRepresentation LearningSemantic SegmentationSimilar Papers 제목 키워드 기반
Masked Clustering Prediction for Unsupervised Point Cloud Pre-training
Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative se…
Unsupervised Pre-trainingSemantic SegmentationContrastive LearningObject DetectionUnsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting…
ClusteringObjectPoint Cloud ClassificationPointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled or weaker forms of annotations. In this…
ClusteringSegmentationSemantic SegmentationUnsupervised Semantic SegmentationPointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to a challenging topic of learning from unlabeled or weaker form of annotations. In thi…
ClusteringSegmentationSemantic SegmentationUnsupervised Semantic SegmentationUnsupervised Multi-Task Feature Learning on Point Clouds
We introduce an unsupervised multi-task model to jointly learn point and shape features on point clouds. We define three unsupervised tasks including clustering, reconstruction, and self-supervised classification to trai…
ClassificationClusteringGeneral ClassificationSegmentation