智能科学与技术学报2024，Vol.6Issue(2)：272-280,9.DOI:10.11959/j.issn.2096-6652.202417
基于自适应平滑度策略的三维模型分类神经架构搜索
Neural architecture search for 3D model classification based on adaptive smoothness strategy
摘要
Abstract
Aiming at the problem of poor generalization ability in hand-crafted architectures that overly rely on expert ex-perience,a neural network architecture search method with an adaptive smoothness strategy was proposed.Firstly,an im-proved candidate operation selection strategy and a continuous relaxation method were used to convert discrete search space into continuous space,and a weight-sharing mechanism was employed to enhance search efficiency.Secondly,a regularization operation with an adaptive smoothness strategy was added to the loss function,whose smoothness degree was controlled by a temperature parameter.Finally,the loss function was calculated using an exponential normalization method to avoid loss value overflow.Experimental results on 3D point cloud datasets and protein-protein interaction data-sets showed that the proposed method achieved higher classification accuracy and more stable performance under the same training samples and iterations.关键词
正则化/神经架构搜索/搜索空间/点云/分类Key words
regularization/neural architecture search/search space/point cloud/classification分类
信息技术与安全科学引用本文复制引用
周鹏,杨军..基于自适应平滑度策略的三维模型分类神经架构搜索[J].智能科学与技术学报,2024,6(2):272-280,9.基金项目
国家自然科学基金项目(No.42261067) （No.42261067）
甘肃省自然科学基金项目(No.22JR11RA157) The National Natural Science Foundation of China(No.42261067),The Natural Science Foundation of Gansu Province(No.22JR11RA157) （No.22JR11RA157）
