Semi-supervised MeshNet classification based on regularization loss

Journal Information

J. Hefei Univ. Tech. (Nat. Sci.), Aug.2023, Vol.46 No.8: 1142-1145, 1152

DOI: 10.3969/j.issn.1003-5060.2023.08.021

Authors

LYU Shuajun $ ^{1} $, XING Yan $ ^{1} $, HONG Peilin $ ^{2} $

(1. School of Mathematics, Hefei University of Technology, Hefei 230601, China; 2. School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei 230012, China)

Abstract and Keywords

Abstract: The application of deep learning in mesh classification has attracted increasing attention. In mesh classification tasks, cross entropy loss is usually used as a loss function. In this paper, a regularization loss based on the structure similarity and geometric consistency of data is proposed, which can be directly added to the loss function to improve the classification accuracy of mesh. According to the final quantitative index of experimental results, the proposed regularization loss has a good effect on improving the accuracy of semi-supervised mesh classification task.

Keywords: regularization loss; mesh classification; semi-supervised learning; MeshNet

作者信息

吕帅君 $ ^{1} $，邢燕 $ ^{1} $，洪沛霖 $ ^{2} $

(1. 合肥工业大学数学学院, 安徽合肥 230601; 2. 安徽中医药大学医药信息工程学院, 安徽合肥 230012)

摘要和关键词

摘要: 深度学习在网格分类中的应用越来越受到人们的关注, 在网格分类任务中, 通常使用交叉熵损失作为损失函数。文章提出一种利用数据的结构相似性和几何一致性的正则化损失, 将其加入损失函数中进行优化, 可有效提高网格的分类准确率。从实验结果的量化指标来看, 提出的正则化损失对于网格半监督分类任务的准确率有很好的提升效果。

关键词: 正则化损失；网格分类；半监督学习；网格网络

Funding

国家自然科学基金资助项目（11601115）；中央高校基本科研业务费专项资金资助项目（PA2020GDSK0060）

合肥工业大学学报(自然科学版)

Navigation