论文标题
3D点云识别对共同腐败的稳健性
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
论文作者
论文摘要
3D点云数据上的深层神经网络已在现实世界中广泛使用，尤其是在安全至关重要的应用中。但是，他们对腐败的鲁棒性的研究较少。在本文中，我们介绍了ModelNet40-C，这是3D Point Cloud腐败鲁棒性的第一个综合基准，由15种常见和现实的腐败组成。我们的评估表明，最先进的模型（SOTA）模型上的ModelNet40和ModelNet40-C上的性能之间存在显着差距。为了减少差距，我们在评估了广泛的增强和测试时间适应策略后，通过将PointCutmix-R和帐篷结合起来，提出一种简单但有效的方法。我们确定了许多关键见解，以实现未来关于腐败鲁棒性的研究。例如，我们揭开了具有适当训练配方的基于变压器的架构，达到了最强的鲁棒性。我们希望我们的深入分析能够激发3D点云领域中强大的培训策略或建筑设计的发展。我们的代码库和数据集包含在https://github.com/jiachens/modelnet40-c中
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the first comprehensive benchmark on 3D point cloud corruption robustness, consisting of 15 common and realistic corruptions. Our evaluation shows a significant gap between the performances on ModelNet40 and ModelNet40-C for state-of-the-art (SOTA) models. To reduce the gap, we propose a simple but effective method by combining PointCutMix-R and TENT after evaluating a wide range of augmentation and test-time adaptation strategies. We identify a number of critical insights for future studies on corruption robustness in point cloud recognition. For instance, we unveil that Transformer-based architectures with proper training recipes achieve the strongest robustness. We hope our in-depth analysis will motivate the development of robust training strategies or architecture designs in the 3D point cloud domain. Our codebase and dataset are included in https://github.com/jiachens/ModelNet40-C
