paper-with-me

홈 › Papers

Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting

2022-02-05 · Guofeng Mei, Litao Yu, Qiang Wu, Jian Zhang, Mohammed Bennamoun

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.

📄 PDF Abstract BibTeX arXiv:2202.02543

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object ClassificationClusteringRepresentation LearningSemantic Segmentation

Similar Papers 제목 키워드 기반

Masked Clustering Prediction for Unsupervised Point Cloud Pre-training

2025-08-12 · Bin Ren, Xiaoshui Huang, Mengyuan Liu, Hong Liu 외 arxiv

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 Detection

Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network

2019-04-28 · Ling Zhang, Zhigang Zhu

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 Classification

PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering

2023-04-18 · Zisheng Chen, Hongbin Xu, Weitao Chen, Zhipeng Zhou 외

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 Segmentation

PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering

2023-01-01 · ICCV 2023 1 · Zisheng Chen, Hongbin Xu, Weitao Chen, Zhipeng Zhou 외

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 Segmentation

Unsupervised Multi-Task Feature Learning on Point Clouds

2019-10-18 · ICCV 2019 10 · Kaveh Hassani, Mike Haley

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