通过注意力引导的对比学习，提升点云模型对薄弱区域的感知能力。
Point Cloud Understanding via Attention-Driven Contrastive Learning
- 用动态掩码让模型关注被忽略的点云区域，强化全局理解
- 结合对比学习损失，在多个数据集上达当前最佳性能
- 特别适合处理噪声多、数据不全的复杂点云场景
近期基于Transformer的点云理解模型虽借助自注意力机制取得进展，但常忽略低显著性区域的信息，导致对扰动敏感且全局理解有限。为此，我们提出PointACL，一种注意力驱动的对比学习框架。该方法采用注意力引导的动态掩码策略，引导模型聚焦于被忽视的区域，增强对点云整体结构的理解；同时将原始预训练损失与对比学习损失结合，提升特征判别力与泛化能力。大量实验验证其有效性：在对象分类、部件分割和少样本学习等任务中均达到当前最优表现。当与Point-MAE、PointGPT等Transformer骨干网络结合时，其在ScanObjectNN、ModelNet40和ShapeNetPart等数据集上均有显著提升，展现出更强的全局与局部特征捕捉能力，以及对扰动和不完整数据的鲁棒性。
原文摘要 · Abstract (English)
Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to perturbations and limited global comprehension. To solve this issue, we introduce PointACL, an attention-driven contrastive learning framework designed to address these limitations. Our method employs an attention-driven dynamic masking strategy that guides the model to focus on under-attended regions, enhancing the understanding of global structures within the point cloud. Then we combine the original pre-training loss with a contrastive learning loss, improving feature discrimination and generalization. Extensive experiments validate the effectiveness of PointACL, as it achieves state-of-the-art performance across a variety of 3D understanding tasks, including object classification, part segmentation, and few-shot learning. Specifically, when integrated with different Transformer backbones like Point-MAE and PointGPT, PointACL demonstrates improved performance on datasets such as ScanObjectNN, ModelNet40, and ShapeNetPart. This highlights its superior capability in capturing both global and local features, as well as its enhanced robustness against perturbations and incomplete data.
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。