Research map / Point clouds / Point cloud classification
Manifold Adversarial Learning for Cross-Domain 3D Shape Representation
Hao Huang, Cheng Chen, Yi Fang
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 |
|---|---|---|---|
| increase adaptive memory size from 100 to 500 (ablation) | Ours (PointNet) · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 69.22 -> 69.84 | Improved |
| increase adaptive memory size from 100 to 500 (ablation) | Ours (PointNet) · ModelNet40 -> ScanObjectNN (Object & Background) | accuracy (%): 57.94 -> 58.36 | Improved |
| use manifold-based adversarial samples instead of additive adversarial (eps=0.1) (ablation) | Ours (PointNet) · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 68.31 -> 69.84 | Improved |
| use manifold-based adversarial samples instead of additive adversarial (eps=0.5) (ablation) | Ours (PointNet) · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 58.37 -> 69.84 | Improved |
| increase additive adversarial strength from eps 0.1 to 0.5 (ablation) | additive adversarial · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 68.31 -> 58.37 | Hurt |
| add manifold adversarial intermediate domains and memory to PointNet | PointNet · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 55.90 -> 69.84 | Improved |
| add manifold adversarial intermediate domains and memory to DGCNN | DGCNN · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 61.68 -> 73.83 | Improved |
| replace random transformation augmentation (MetaSets) with manifold adversarial transformations | DGCNN backbone · ModelNet40 -> ScanObjectNN (Object) | accuracy (%): 72.42 -> 73.83 | Improved |
| replace MetaSets with manifold adversarial method | PointNet · ShapeNet -> ScanObjectNN (Object) | accuracy (%): 55.25 -> 57.03 | Improved |
| replace MetaSets with manifold adversarial method | DGCNN · ShapeNet -> ScanObjectNN (Object & Background) | accuracy (%): 59.08 -> 61.13 | Improved |
| replace MetaSets with manifold adversarial method | PointNet · ModelNet40 -> ScanObjectNN (Object & Background) | accuracy (%): 57.19 -> 58.36 | Improved |
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.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · 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)
- MetaSets: Meta-Learning on Point Sets for Generalizable Representations (CVPR 2021 · similarity 0.91)
- Learning Generalizable Part-based Feature Representation for 3D Point Clouds (NeurIPS 2022 · similarity 0.90)
- Multi-Scale Part-Based Feature Representation for 3D Domain Generalization and Adaptation (TPAMI 2024 · similarity 0.89)
- Learning Representations and Generative Models for 3D Point Clouds (ICML 2018 · similarity 0.89)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · 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.
