论文标题
连贯的分层多标签分类网络
Coherent Hierarchical Multi-Label Classification Networks
论文作者
论文摘要
分层多标签分类（HMC）是一项具有挑战性的分类任务，通过对这些类施加层次结构约束来扩展标准多标签分类问题。在本文中，我们提出了一种用于HMC问题的新方法C-HMCNN（H），该方法给定了基础多标签分类问题的网络H，利用了层次结构信息，以产生与约束并提高性能相一致的预测。我们进行了广泛的实验分析，表明与最新模型相比，C-HMCNN（H）的表现出色。
Hierarchical multi-label classification (HMC) is a challenging classification task extending standard multi-label classification problems by imposing a hierarchy constraint on the classes. In this paper, we propose C-HMCNN(h), a novel approach for HMC problems, which, given a network h for the underlying multi-label classification problem, exploits the hierarchy information in order to produce predictions coherent with the constraint and improve performance. We conduct an extensive experimental analysis showing the superior performance of C-HMCNN(h) when compared to state-of-the-art models.
