通过采样差异与权重平均，提升点云分类模型在测试时的鲁棒性。
Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging
- 利用FPS和KNN生成多组点云表示，对每组进行TENT适应
- 在ModelNet40-C等3个数据集上均优于现有方法，提升显著
- 无需额外数据，计算开销小，适合部署于真实场景
测试时自适应（TTA）通过在无源数据访问条件下调整预训练模型来应对测试阶段的分布偏移。本文提出一种针对3D点云分类的新颖TTA方法，结合采样变化与权重平均。该方法采用最远点采样（FPS）和K近邻（KNN）生成多个点云表示，使用TENT算法对每种变化进行模型适应，并通过平均适应后的权重获得最终参数，从而提升对分布偏移的鲁棒性。在ModelNet40-C、ShapeNet-C和ScanObjectNN-C数据集上的大量实验表明，无论采用Point-MAE、PointNet还是DGCNN作为主干网络，本方法均持续优于现有方法，且资源开销极低。所提方法有效增强了模型在复杂现实条件下的泛化能力与稳定性。
原文摘要 · Abstract (English)
Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data. In this work, we propose a novel TTA approach for 3D point cloud classification, combining sampling variation with weight averaging. Our method leverages Farthest Point Sampling (FPS) and K-Nearest Neighbors (KNN) to create multiple point cloud representations, adapting the model for each variation using the TENT algorithm. The final model parameters are obtained by averaging the adapted weights, leading to improved robustness against distribution shifts. Extensive experiments on ModelNet40-C, ShapeNet-C, and ScanObjectNN-C datasets, with different backbones (Point-MAE, PointNet, DGCNN), demonstrate that our approach consistently outperforms existing methods while maintaining minimal resource overhead. The proposed method effectively enhances model generalization and stability in challenging real-world conditions.
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。