Journal of Nanobiotechnology BioMed Central
Journal of Nanobiotechnology BioMed Central
复制标题
DOI：
10.1109/tip.2019.2913986
复制
发表时间：
2008
影响因子：
10.6
通讯作者：
中科院分区：
文献类型：
--
作者：
在本文中，介绍了一种新的半监督学习技术的基础上，一个简单的迭代学习周期与学习阈值技术和集成决策支持系统。在训练深度学习的分类模型时，通过使用未标记数据来展示最先进的模型性能和增加的训练数据量。所提出的方法独立于模型架构或损失函数，使这种方法适用于广泛的机器学习和分类任务。在评估半监督学习技术和一些更具挑战性的图像分类数据集（CIFAR-100和ImageNet的200类子集）时，对常用数据集进行了评估。
Within this paper, a novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. The state-of-the-art model performance and increased training data volume are demonstrated through the use of unlabeled data when training deeply learned classification models. The methods presented work independently from the model architectures or loss functions, making this approach applicable to a wide range of machine learning and classification tasks. Evaluation of the proposed approach is performed on commonly used datasets when evaluating semi-supervised learning techniques and a number of more challenging image classification datasets (CIFAR-100 and a 200 class subset of ImageNet).