摘要
Dynamic point cloud videos exhibit intricate spatio-temporal coupling. Current end-to-end methods are only evaluated on specific datasets and tasks, generalize poorly across scenes or tasks, and must be retrained from scratch. To uncover transferable universal priors, we refocus our investigation on static point cloud foundation models. In this paper, we first identify two bottlenecks in existing transfer learning methods: Heavy computation and redundant design. To obtain a compact and lightweight solution, we propose an efficient cross-modal transfer method that uses progressive adapters. It reduces self-attention from quadratic to linear complexity with non-overlapping sliding window attention. A shuffled Hilbert-Z bidirectional scan curve converts the dynamic point cloud video into a Mamba-compatible feature sequence; progressive gating fusion then lets the foundation model and the newly added adapter cooperate efficiently. The foundation model weights remain unchanged and no external auxiliary designs are required. Experiments on MSR-Action3D, HOI4D and SHREC'17 show that tuning only 1.8% of the parameters already surpasses existing baselines, confirming the superiority of our method.
| 投稿的翻译标题 | Efficient Transfer Learning for Dynamic Point Clouds With Progressive Adapters |
|---|---|
| 源语言 | 繁体中文 |
| 页(从-至) | 1710-1720 |
| 页数 | 11 |
| 期刊 | Zidonghua Xuebao/Acta Automatica Sinica |
| 卷 | 52 |
| 期 | 8 |
| DOI | |
| 出版状态 | 已出版 - 8月 2026 |
| 已对外发布 | 是 |
关键词
- attention mechanism
- efficient adapter
- hybrid architecture
- point cloud video
- transfer learning
学术指纹
探究 '基于渐进式适配器的动态点云高效迁移学习方法' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver