Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adversarial Distillation (FAD) method, a generic adversarial loss function in point cloud distillation, to reduce loss during knowledge transfer.In the feature extraction stage, the features extracted by the teacher are used as the discriminator, and the students continuously generate new features in the training stage. The feature of the student is obtained by attacking the feedback from the teacher and getting a score to judge whether the student has learned the knowledge well or not. In experiments on standard point cloud classification on ModelNet40 and ScanObjectNN datasets, our method reduced the information loss of knowledge transfer in distillation in 40x model compression while maintaining competitive performance.

翻译：由于点云具有不规则且无序的几何结构，传统知识蒸馏技术直接应用于点云任务时会丢失大量信息。本文提出特征对抗蒸馏（Feature Adversarial Distillation, FAD）方法，一种用于点云蒸馏的通用对抗损失函数，以降低知识迁移过程中的损失。在特征提取阶段，教师网络提取的特征被用作判别器，学生网络在训练过程中不断生成新特征。学生网络的特征通过攻击教师网络的反馈获得，并得到评分以判断学生是否充分掌握了知识。在ModelNet40和ScanObjectNN数据集上的标准点云分类实验中，我们的方法在实现40倍模型压缩的同时，凭借具有竞争力的性能降低了蒸馏过程中知识迁移的信息损失。