基于梯形网络和改进三训练法的半监督分类  

Semi-supervised Classification Model Based on Ladder Network and Improved Tri-training

作　　者：莫建文[1] 贾鹏 MO Jian-Wen;JIA Peng(School of Information and Communications,Guilin University of Electronic Science and Technology,Guilin 541000)

机构地区：[1]桂林电子科技大学信息与通信学院,桂林541000

出　　处：《自动化学报》2022年第8期2088-2096,共9页Acta Automatica Sinica

基　　金：国家自然科学基金(61661017,61967005,U1501252);广西自然科学基金(2017GXNSFBA198212);桂林电子科技大学研究生创新项目基金(2019YCXS020)资助。

摘　　要：为了提高半监督深层生成模型的分类性能,提出一种基于梯形网络和改进三训练法的半监督分类模型.该模型在梯形网络框架有噪编码器的最高层添加3个分类器,结合改进的三训练法提高图像分类性能.首先,用基于类别抽样的方法将有标记数据分为3份,模型以有标记数据的标签误差和未标记数据的重构误差相结合的方式调整参数,训练得到3个Large-margin Softmax分类器;接着,用改进的三训练法对未标记数据添加伪标签,并对新的标记数据分配不同权重,扩充训练集;最后,利用扩充的训练集更新模型.训练完成后,对分类器进行加权投票,得到分类结果.模型得到的梯形网络的特征有更好的低维流形表示,可以有效地避免因为样本数据分布不均而导致的分类误差,增强泛化能力.模型分别在MNIST数据库,SVHN数据库和CIFAR10数据库上进行实验,并且与其他半监督深层生成模型进行了比较,结果表明本文所提出的模型得到了更高的分类精度.In order to improve the classification performance of semi-supervised deep generation models,a new model based on ladder network and improved tri-training algorithm is proposed.This model adds three classifiers to the highest layer of the noisy coding layer of the ladder network,and improves the image classification performance by combining the improved tri-training.First,the labeled data is divided into three parts by using a class-based sampling method.The model adjusts the parameters by combining the labeled error of labeled data and the reconstruction error of unlabeled data,and is trained to get three Large-margin Softmax classifiers.Next,the improved tri-training algorithm is developed to add pseudo-labels to the unlabeled data,and different weights are assigned to the new labeled data to expand the training set.Finally,the expanded training set is applied to update the model.After the above practice,a weighted voting is performed on the classifier to obtain the classification result.The characteristics of the ladder network obtained by this model have better low-dimensional manifold representations,which can effectively avoid classification error caused by uneven distribution of sample data and enhance generalization ability.The model is tested on the MNIST,SVHN and CIFAR10 respectively.In comparison with other semisupervised deep generation models,test results show that the model proposed in this paper has obtained state-of-theart classification accuracy over existing semi-supervised learning methods.

关 键 词：梯形网络 改进的三训练法 半监督学习 Large-margin Softmax分类器 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]