Despite recent advancements in deep neural networks for point cloud recognition, real-world safety-critical applications present challenges due to unavoidable data corruption. Current models often fall short in generalizing to unforeseen distribution shifts. In this study, we harness the inherent set property of point cloud data to introduce a novel critical subset identification (CSI) method, aiming to bolster recognition robustness in the face of data corruption. Our CSI framework integrates two pivotal components: density-aware sampling (DAS) and self-entropy minimization (SEM), which cater to static and dynamic CSI, respectively. DAS ensures efficient robust anchor point sampling by factoring in local density, while SEM is employed during training to accentuate the most salient point-to-point attention. Evaluations reveal that our CSI approach yields error rates of 18.4\% and 16.3\% on ModelNet40-C and PointCloud-C, respectively, marking a notable improvement over state-of-the-art methods by margins of 5.2\% and 4.2\% on the respective benchmarks. Code is available at \href{https://github.com/masterwu2115/CSI/tree/main}{https://github.com/masterwu2115/CSI/tree/main}

翻译：尽管深度神经网络在点云识别领域取得近期进展，但现实世界中的安全关键型应用仍因不可避免的数据损毁而面临挑战。现有模型在泛化到未知分布偏移时往往表现不足。本研究利用点云数据固有的集合特性，提出了一种新型关键子集识别（CSI）方法，旨在提升面对数据损毁时的识别鲁棒性。我们的CSI框架整合了两个核心组件：密度感知采样（DAS）和自熵最小化（SEM），分别服务于静态和动态CSI。DAS通过考虑局部密度实现高效的鲁棒锚点采样，而SEM在训练过程中用于突出最显著的点间注意力。评估表明，我们的CSI方法在ModelNet40-C和PointCloud-C数据集上的错误率分别达到18.4%和16.3%，相比当前最优方法在两个基准上分别实现了5.2%和4.2%的显著改进。代码发布于\href{https://github.com/masterwu2115/CSI/tree/main}{https://github.com/masterwu2115/CSI/tree/main}