计算机科学
判别式
过度拟合
人工智能
机器学习
聚类分析
正规化(语言学)
一致性(知识库)
模式识别(心理学)
数据挖掘
人工神经网络
作者
Hui Tang,Lin Sun,Kui Jia
标识
DOI:10.1007/978-3-031-19821-2_19
摘要
AbstractSemi-supervised learning (SSL) has achieved new progress recently with the emerging framework of self-training deep networks, where the criteria for selection of unlabeled samples with pseudo labels play a key role in the empirical success. In this work, we propose such a new criterion based on consistency among multiple, stochastic classifiers, termed Stochastic Consensus (STOCO). Specifically, we model parameters of the classifiers as a Gaussian distribution whose mean and standard deviation are jointly optimized during training. Due to the scarcity of labels in SSL, modeling classifiers as a distribution itself provides additional regularization that mitigates overfitting to the labeled samples. We technically generate pseudo labels using a simple but flexible framework of deep discriminative clustering, which benefits from the overall structure of data distribution. We also provide theoretical analysis of our criterion by connecting with the theory of learning from noisy data. Our proposed criterion can be readily applied to self-training based SSL frameworks. By choosing the representative FixMatch as the baseline, our method with multiple stochastic classifiers achieves the state of the art on popular SSL benchmarks, especially in label-scarce cases.KeywordsSemi-supervised learningStochastic classifiersConsistency criterionDeep discriminative clustering
科研通智能强力驱动
Strongly Powered by AbleSci AI