提出StruMamba3D，用结构感知Mamba提升点云自监督表征学习效果
StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
- 设计空间状态代理，保留点间空间依赖关系
- 在ModelNet40上达95.1%准确率，ScanObjectNN挑战集92.75%无需投票
- 解决长序列输入敏感问题，适合点云结构建模任务
近期基于Mamba的方法通过状态空间模型（SSM）实现了高效的上下文建模和线性复杂度，在点云表征学习中表现优异。然而，这些方法仍存在两大关键问题：处理过程中破坏了3D点的空间邻近性，且在下游任务中随着输入长度增加无法保持长序列记忆。为此，我们提出StruMamba3D，一种新型自监督点云表征学习范式。首先，设计空间状态并作为代理以保留点间空间依赖；其次，通过状态级更新策略增强SSM，并引入轻量卷积促进空间状态间的交互，实现高效结构建模；第三，通过序列长度自适应策略降低预训练Mamba模型对输入长度变化的敏感性。在四个下游任务上的实验表明该方法性能优越。尤其在ModelNet40上达到95.1%准确率，在最具有挑战性的ScanObjectNN数据集分割上达92.75%准确率，且无需投票策略。
原文摘要 · Abstract (English)
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods still face two key issues that limit the potential of SSM: Destroying the adjacency of 3D points during SSM processing and failing to retain long-sequence memory as the input length increases in downstream tasks. To address these issues, we propose StruMamba3D, a novel paradigm for self-supervised point cloud representation learning. It enjoys several merits. First, we design spatial states and use them as proxies to preserve spatial dependencies among points. Second, we enhance the SSM with a state-wise update strategy and incorporate a lightweight convolution to facilitate interactions between spatial states for efficient structure modeling. Third, our method reduces the sensitivity of pre-trained Mamba-based models to varying input lengths by introducing a sequence length-adaptive strategy. Experimental results across four downstream tasks showcase the superior performance of our method. In addition, our method attains the SOTA 95.1% accuracy on ModelNet40 and 92.75% accuracy on the most challenging split of ScanObjectNN without voting strategy.
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。