Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
超越防御:面向内在3D点云鲁棒性的流形对齐正则化
机构 * School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算机与人工智能学院,西南交通大学) ; Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Southwest Jiaotong University(可持续城市智能交通工程研究中心,教育部,西南交通大学)
专题命中 点云 :point cloud(title,abstract);分类 cs.CV
AI总结 提出流形对齐点识别(MAPR)框架,通过正则化潜在几何结构并施加内在扰动一致性损失,在不依赖对抗训练或额外数据的情况下显著提升点云模型对多种攻击的鲁棒性。