论文标题
开放设定的学习通过利用未标记的数据通过增强类别
Open-set learning with augmented categories by exploiting unlabelled data
论文作者
论文摘要
新型类别通常被定义为在训练过程中未观察到的类别，但在测试过程中存在。但是，部分标记的培训数据集可以包含属于新型类别的未标记培训样本，这意味着这些样本可以在培训和测试中存在。这项研究是在我们所谓的新学习政策中，我们称之为观察到的novel和未观察到的新颖性类别之间的研究，称为开放式学习，并通过利用未标记的数据或开放式LACU来使用增强类别。在调查了现有的学习政策之后，我们将Open-Lacu作为积极和未标记的学习，半监督学习和开放式认可的统一政策。随后，我们使用相关研究领域的算法培训过程开发了第一个开放式LACU模型。拟议的开放LACU分类器可实现最先进的和首先的结果。
Novel categories are commonly defined as those unobserved during training but present during testing. However, partially labelled training datasets can contain unlabelled training samples that belong to novel categories, meaning these can be present in training and testing. This research is the first to generalise between what we call observed-novel and unobserved-novel categories within a new learning policy called open-set learning with augmented category by exploiting unlabelled data or Open-LACU. After surveying existing learning policies, we introduce Open-LACU as a unified policy of positive and unlabelled learning, semi-supervised learning and open-set recognition. Subsequently, we develop the first Open-LACU model using an algorithmic training process of the relevant research fields. The proposed Open-LACU classifier achieves state-of-the-art and first-of-its-kind results.
