Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbations. In this paper, we delve into boosting the general robustness of point cloud recognition models and propose Point-Cloud Contrastive Adversarial Training (PointCAT). The main intuition of PointCAT is encouraging the target recognition model to narrow the decision gap between clean point clouds and corrupted point clouds. Specifically, we leverage a supervised contrastive loss to facilitate the alignment and uniformity of the hypersphere features extracted by the recognition model, and design a pair of centralizing losses with the dynamic prototype guidance to avoid these features deviating from their belonging category clusters. To provide the more challenging corrupted point clouds, we adversarially train a noise generator along with the recognition model from the scratch, instead of using gradient-based attack as the inner loop like previous adversarial training methods. Comprehensive experiments show that the proposed PointCAT outperforms the baseline methods and dramatically boosts the robustness of different point cloud recognition models, under a variety of corruptions including isotropic point noises, the LiDAR simulated noises, random point dropping and adversarial perturbations.
翻译:尽管在各种应用中取得了显著的成绩,但点云识别模型往往受到自然腐败和对抗性扰动的影响。在本文件中,我们探讨了如何提高点云识别模型的总体稳健性,并提出了点-点对点反对面培训(PoCAT)。PointCAT的主要直觉是鼓励缩小清洁点云和腐败点云之间决策差距的目标识别模型。具体地说,我们利用监督的对比损失来帮助识别模型所提取的超视界特征的一致和统一,并设计一对与动态原型指南的集中损失,以避免这些特征偏离其所属类别。为了提供更具挑战性的点云,我们用对抗性的方法将噪声生成器与从刮起的识别模型一起培训,而不是像以往的对抗性培训方法一样,使用基于梯度的攻击作为内环。全面实验表明,拟议的点CAT超越了基线方法,在各种腐败下,包括按摄氏点噪声、LIDAR模拟对点的对称性噪声、随机压点压压和随机压定点下,大大提升了不同点云度识别模型的坚固性。