基于对比学习的三维模型分类

打开文本图片集

关键词：三维模型分类；对比学习；卷积神经网络；注意力机制；迁移学习DOI：10.15938/j. jhust.2025.02.004中图分类号：TP391 文献标志码：A 文章编号：1007-2683（2025）02-0032-10

Abstract：At present，3Dmodelclasification hasbeenaresearch hotspot.Masive3Dmodels notonlyhavediversityineach class，butalsoavesimilaritisbetweenclases，whichseriouslyafect theclasificationaccuracyof3Dmodels.Weproposea3D modelclassficatiomethodbasedootrastielaingIntstod，thengisdidedintompledisiatioagead aclassifictionstage.Inthestageofsamplediscrimination，3Dmodelsofthesamecategoryaremutuallpositivesamples，and3D modelsofothercategoriesaremutuallyegativesampls.Thecontrastivelossisusedtoconstraintesamplefatures，ndtepositive andnegativesamplesareappedtothesingle-centerunithypersphereinthesamespace toobtainagoodsemanticrepresentationspace of3Dmodellasification.Inaditon，inodertocapturethecorelatinbetweentheviewsandthekeyareasintheviews，amultiheadslf-attentionmoduleandspatialatentionmoduleareintroducedinteaper.Moreover，thechaelatentionisddednthe multi-headself-atentionmoduletoobtainthechanneldimensioninformation.Intheclasificationstage，thenetworkmodelis trasferredtotheclassficationtaskbyfine-uningtenetworkparametrstocompletethe3Dmodelclasification.Theexperiental results show that the classification accuracy of the 3D model respectively reaches 99.4% and 97.5% on the ModelNet1O and ModelNet40 datasets.

Keywords：3Dmodel classification；contrastive learning；convolutionneural network；atention mechanism；transferleaing

0 引言

人类的视觉感知具有三维立体性，并且三维模型相较于文本、图像等拥有更加丰富的信息，因而三维模型在机器人、工业设计、无人驾驶等新兴领域有着举足轻重的作用。（剩余16242字）