Research map / Point clouds / Point cloud classification
Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds
Longkun Zou, Hui Tang, Ke Chen, Kui Jia
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add SPST to RotCls+LocCls (ablation) | GAST · PointDA-10 average | accuracy (%): 69.5 -> 73.0 | Improved |
| add RotCls to LocCls (ablation) | GAST · PointDA-10 average | accuracy (%): 65.1 -> 69.5 | Improved |
| add LocCls to RotCls (ablation) | GAST · PointDA-10 average | accuracy (%): 63.7 -> 69.5 | Improved |
| add LocCls only to the w/o Adapt baseline (ablation) | DGCNN · PointDA-10 average | accuracy (%): 62.2 -> 65.1 | Improved |
| add RotCls only to the w/o Adapt baseline (ablation) | DGCNN · PointDA-10 average | accuracy (%): 62.2 -> 63.7 | Improved |
| add SPST only to the w/o Adapt baseline (ablation) | DGCNN · PointDA-10 average | accuracy (%): 62.2 -> 65.8 | Improved |
| add SPST to RotCls+LocCls (ablation) | GAST · PointDA-10 M->S* | accuracy (%): 56.7 -> 59.8 | Improved |
| add SPST to RotCls+LocCls (ablation) | GAST · PointDA-10 S*->M | accuracy (%): 73.4 -> 81.1 | Improved |
| add SPST to RotCls+LocCls (ablation) | GAST · PointDA-10 M->S* class-wise average | accuracy (%): 52.2 -> 54.5 | Improved |
| full GAST versus DefRec + PCM | GAST · PointDA-10 average | accuracy (%): 68.6 -> 73.0 | Improved |
| full GAST versus w/o Adapt on synthetic-to-real tasks | DGCNN · PointDA-10 M->S* | accuracy (%): 43.8 -> 59.8 | Improved |
| full GAST versus DefRec + PCM on long-tailed classes | GAST · PointDA-10 M->S* Bathtub and Bed | accuracy (%): 65.4 -> 57.7 | No 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.
- PointDAN — PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation (NeurIPS 2019) · better on 2 of 2 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
- Domain Adaptation on Point Clouds via Geometry-Aware Implicits (CVPR 2022 · similarity 0.92)
- Self-Supervised Global-Local Structure Modeling for Point Cloud Domain Adaptation With Reliable Voted Pseudo Labels (CVPR 2022 · similarity 0.89)
- PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation (NeurIPS 2019 · similarity 0.89)
- Shape Self-Correction for Unsupervised Point Cloud Understanding (ICCV 2021 · similarity 0.89)
- Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds (CVPR 2020 · similarity 0.89)
- PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label (ICCV 2023 · similarity 0.88)
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.
