Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

March 30, 2020 · Entered Twilight · 🏛 European Conference on Computer Vision

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, data_utils, models, pretrain_partseg_shapenet.py, provider.py, test_acdfeat_modelnet.py, train_partseg_shapenet_multigpu.py, viewsegbatch.py

Authors Matheus Gadelha, Aruni RoyChowdhury, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang, Subhransu Maji arXiv ID 2003.13834 Category cs.CV: Computer Vision Cross-listed cs.GR, cs.LG Citations 47 Venue European Conference on Computer Vision Repository https://github.com/matheusgadelha/PointCloudLearningACD ⭐ 40 Last Checked 1 month ago

Abstract

The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for statistically efficient methods to learn 3D shape representations. In this paper, we investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations. We show that using ACD to approximate ground truth segmentation provides excellent self-supervision for learning 3D point cloud representations that are highly effective on downstream tasks. We report improvements over the state-of-the-art for unsupervised representation learning on the ModelNet40 shape classification dataset and significant gains in few-shot part segmentation on the ShapeNetPart dataset.Code available at https://github.com/matheusgadelha/PointCloudLearningACD