Research map / Point clouds / Point cloud classification
PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification
Hao Yang, Qianyu Zhou, Haijia Sun, Xiangtai Li, Xuequan Lu, Lizhuang Ma, Shuicheng YAN
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 AGT-Shift to V-RWKV baseline (ablation) | V-RWKV · PointDA-10 | avg accuracy: 72.24 -> 73.57 | Improved |
| add CD-KDA to V-RWKV baseline (ablation) | V-RWKV · PointDA-10 | avg accuracy: 72.24 -> 74.28 | Improved |
| combine AGT-Shift and CD-KDA (ablation) | V-RWKV · PointDA-10 | avg accuracy: 72.24 -> 75.66 | Improved |
| use AGT-Shift instead of KNN-based token shifts (ablation) | PointDGRWKV · PointDA-10 | avg accuracy: 74.82 -> 75.66 | Improved |
| align only keys rather than values in CD-KDA (ablation) | CD-KDA · PointDA-10 | avg accuracy: 74.08 -> 75.66 | Improved |
| also align values in addition to keys (ablation) | CD-KDA · PointDA-10 | avg accuracy: 75.66 -> 75.68 | No clear effect |
| scale up network (larger dim, denser sampling) (ablation) | PointDGRWKV · PointDA-10 | avg accuracy: 75.66 -> 76.13 | Improved |
| halve number of blocks (ablation) | PointDGRWKV · PointDA-10 | avg accuracy: 75.66 -> 75.15 | Hurt |
| PointDGRWKV vs PointDGMamba | PointDG-3to1 · PointDG-3to1 | avg accuracy: 80.53 -> 81.92 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PointDGMamba — PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model (AAAI 2025) · better on 3 of 3 shared results
- MetaSets — MetaSets: Meta-Learning on Point Sets for Generalizable Representations (CVPR 2021) · better on 1 of 1 shared result
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
- PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model (AAAI 2025 · similarity 0.93)
- DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding (ECCV 2024 · similarity 0.90)
- PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning (AAAI 2025 · similarity 0.90)
- Learning Generalizable Part-based Feature Representation for 3D Point Clouds (NeurIPS 2022 · similarity 0.88)
- PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation (NeurIPS 2019 · similarity 0.88)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · similarity 0.87)
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.
