arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.13682cs.LGcs.NEstat.ML
收藏

基于半监督自组织映射的深度分类

Deep Categorization with Semi-Supervised Self-Organizing Maps

Universidade Federal de Pernambuco(伯南布哥联邦大学);Center of Informatics - CIn(信息中心)

Pedro H. M. Braga, Heitor R. Medeiros, Hansenclever F. Bassani

摘要:

如今,随着技术的进步,每天都会产生越来越多的非结构化数据。然而,这是一个痛苦的工作,标签和组织。标签是一个昂贵的,耗时的,困难的任务。它通常是手动完成的,这与数据中的噪声和错误相结合。因此,开发可以从标记和未标记数据中受益的智能模型非常重要。目前,无监督学习和半监督学习的研究工作仍然被纯监督学习的成功所掩盖。然而,预计从长远来看,它们将变得更加重要。本文提出了一种半监督模型,称为批处理半监督自组织映射(Batch SS-SOM),它是SOM的扩展,结合了深度学习兴起时的一些进步,如批处理训练。实验结果表明,Batch SS-SOM是一种很好的半监督分类和聚类方法。它在准确性和聚类误差方面表现良好,即使是少量的标记样本,以及当呈现给无监督数据时,并且在传统图像分类基准数据集中的迁移学习场景中显示出竞争力。

英文摘要:

Nowadays, with the advance of technology, there is an increasing amount of unstructured data being generated every day. However, it is a painful job to label and organize it. Labeling is an expensive, time-consuming, and difficult task. It is usually done manually, which collaborates with the incorporation of noise and errors to the data. Hence, it is of great importance to developing intelligent models that can benefit from both labeled and unlabeled data. Currently, works on unsupervised and semi-supervised learning are still being overshadowed by the successes of purely supervised learning. However, it is expected that they become far more important in the longer term. This article presents a semi-supervised model, called Batch Semi-Supervised Self-Organizing Map (Batch SS-SOM), which is an extension of a SOM incorporating some advances that came with the rise of Deep Learning, such as batch training. The results show that Batch SS-SOM is a good option for semi-supervised classification and clustering. It performs well in terms of accuracy and clustering error, even with a small number of labeled samples, as well as when presented to unsupervised data, and shows competitive results in transfer learning scenarios in traditional image classification benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑