Neural architecture search for 3D model classification based on adaptive smoothness strategy
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.
国家科技期刊平台
NSTL
万方数据
