FPSMix: data augmentation strategy for point cloud classification  

作　　者：Taiyan CHEN Xianghua YING 

机构地区：[1]Key Lab of Machine Perception(MoE),School of Intelligence Science and Technology,Peking University,Beijing 100871,China

出　　处：《Frontiers of Computer Science》2025年第2期105-113,共9页计算机科学前沿(英文版)

基　　金：supported by the National Key R&D Program of China(No.2020YFB1708002);the National Natural Science Foundation of China(Grant Nos.62371009 and 61971008).

摘　　要：Data augmentation is a widely used regularization strategy in deep neural networks to mitigate overfitting and enhance generalization.In the context of point cloud data,mixing two samples to generate new training examples has proven to be effective.In this paper,we propose a novel and effective approach called Farthest Point Sampling Mix(FPSMix)for augmenting point cloud data.Our method leverages farthest point sampling,a technique used in point cloud processing,to generate new samples by mixing points from two original point clouds.Another key innovation of our approach is the introduction of a significance-based loss function,which assigns weights to the soft labels of the mixed samples based on the classification loss of each part of the new sample that is separated from the two original point clouds.This way,our method takes into account the importance of different parts of the mixed sample during the training process,allowing the model to learn better global features.Experimental results demonstrate that our FPSMix,combined with the significance-based loss function,improves the classification accuracy of point cloud models and achieves comparable performance with state-of-the-art data augmentation methods.Moreover,our approach is complementary to techniques that focus on local features,and their combined use further enhances the classification accuracy of the baseline model.

关 键 词：point cloud classification data augmentation loss function point cloud understanding point cloud analysis 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]