跳到主要导航 跳到搜索 跳到主要内容

基于渐进式适配器的动态点云高效迁移学习方法

  • Yi Ding Sun
  • , Ji Hua Zhu
  • , Yao Nan Wang
  • , Hao Zhe Cheng
  • , Chao Yi Lu
  • , Lin Chen
  • Xi'an Jiaotong University
  • National Key Laboratory of Human–Machine Hybrid Augmented Intelligence
  • School of Artificial Intelligence and Robotics
  • Hunan University
  • National Engineering Research Center for Robot Visual Perception and Control Technology

科研成果: 期刊稿件 › 文章 › 同行评审

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