用强化学习提升点云少样本学习效果，显著优于传统方法
PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning
- 设计奖励函数实现点云的显式强化微调
- 少样本分类任务上超越监督微调，性能更稳定
- 适合数据稀缺场景下的3D模型优化
理解点云中的空间动态与语义是实现全面3D理解的基础。尽管基于强化学习的算法（如组相对策略优化，GRPO）在大语言模型中通过精心设计的奖励机制显著提升了推理能力，但在3D感知领域仍鲜有探索。本文提出PointRFT，首个专为点云表示学习设计的强化微调范式。选取三种主流3D基础模型，设计准确率奖励与分散性奖励函数以稳定训练并缓解分布偏移。通过对比多种训练范式的少样本分类实验，结果表明PointRFT在多个基准上持续优于标准监督微调（SFT）。进一步将PointRFT融入预训练-微调-强化（Pretraining-SFT-RFT）混合范式后，点云基础模型的表征能力被充分释放，在数据稀缺场景下达到当前最优性能。
原文摘要 · Abstract (English)
Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable breakthroughs in large language models by incentivizing reasoning capabilities through strategic reward design, their potential remains largely unexplored in the 3D perception domain. This naturally raises a pivotal question: Can RL-based methods effectively empower 3D point cloud fine-tuning? In this paper, we propose PointRFT, the first reinforcement fine-tuning paradigm tailored specifically for point cloud representation learning. We select three prevalent 3D foundation models and devise specialized accuracy reward and dispersion reward functions to stabilize training and mitigate distribution shifts. Through comprehensive few-shot classification experiments comparing distinct training paradigms, we demonstrate that PointRFT consistently outperforms vanilla supervised fine-tuning (SFT) across diverse benchmarks. Furthermore, when organically integrated into a hybrid Pretraining-SFT-RFT paradigm, the representational capacity of point cloud foundation models is substantially unleashed, achieving state-of-the-art performance particularly under data-scarce scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。