AI Paper Atlas

Research map / Point clouds / Point cloud classification

ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling

Xinglin Li, Jiajing Chen, Jinhui Ouyang, Hanhui Deng, Senem Velipasalar, Di Wu

CVPR 2023 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Recycle discarded point features and align them with max-pooled features (ablation)ToThePoint · ScanObjectNNSVM accuracy: 61.45% -> 74.70% (PointNet); 80.38% -> 81.93% (DGCNN)Improved
Use two branches instead of one, retaining recycling (ablation)ToThePoint · ScanObjectNNSVM accuracy: 7.06%; 8.27% accuracy reduction with one branch (PointNet; DGCNN)Improved
Use two branches instead of one, retaining recycling (ablation)ToThePoint · ModelNet40SVM accuracy: 2.76%; 0.41% accuracy reduction with one branch (PointNet; DGCNN)Improved
Add recycling to the two-branch model (ablation)ToThePoint · ModelNet40SVM accuracy: 6.89%; 0.37% accuracy reduction without recycling (PointNet; DGCNN)Improved
Add recycling to the two-branch model (ablation)ToThePoint · ScanObjectNNSVM accuracy: 13.25%; 1.56% accuracy reduction without recycling (PointNet; DGCNN)Improved
Use ToThePoint pretraining rather than CrossPointDGCNN · ModelNet40-C (LiDAR, severity 1)accuracy: 83.69±0.29 -> 83.80±0.32Improved
Use ToThePoint pretraining rather than CrossPointPointNet · ModelNet40-C (LiDAR, severity 1)accuracy: 81.12±0.44 -> 80.97±0.27Hurt
Use ToThePoint pretraining rather than the strongest listed baselinePointNet and DGCNN · ScanObjectNNSVM accuracy: 73.67 -> 74.70 (PointNet); 81.43 -> 81.93 (DGCNN)Improved
Use ToThePoint pretraining rather than CrossPointDGCNN · ModelNet40, 5-way 10-shotaccuracy: 91.12 ± 4.93 -> 92.73 ± 4.79Improved
Use ToThePoint pretraining rather than CrossPointDGCNN · ModelNet40, 5-way 20-shotaccuracy: 94.56 ± 3.23 -> 95.10 ± 2.95Improved
Use ToThePoint pretraining rather than CrossPointDGCNN · ScanObjectNN, 5-way 10-shotaccuracy: 77.24 ±7.13 -> 78.13 ± 7.29Improved
Use ToThePoint pretraining rather than CrossPointPointNet · ScanObjectNN, 10-way 10-shotaccuracy: 66.61 ±3.96 -> 66.71 ± 5.40No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy