Deep MIML Network
Deep MIML Network
复制标题
DOI：
10.1609/aaai.v31i1.10890
复制
发表时间：
2017-02
期刊：
影响因子：
--
通讯作者：
Ji Feng;Zhi-Hua Zhou
中科院分区：
文献类型：
--
作者：
Ji Feng;Zhi-Hua Zhou
在许多真实的应用中，所关注的对象具有多个标签，并且可以表示为一组实例。多实例多标记（MIML）学习提供了一个框架来处理这样的任务，并在各个领域表现出优异的性能。在MIML环境中，实例的特征表示通常对最终性能有很大影响;受最近深度学习研究的启发，本文提出了DeepMIML网络，该网络利用深度神经网络形成来生成MIML的实例表示。DeepMIML结构的子概念学习组件保留了MIML算法的实例-标签关系发现能力;也就是说，它可以自动定位触发标签的关键输入模式。通过在不同数据域上的实验验证了DeepMIML网络的有效性。
In many real world applications, the concerned objects are with multiple labels, and can be represented as a bag of instances. Multi-instance Multi-label (MIML) learning provides a framework for handling such task and has exhibited excellent performance in various domains. In a MIML setting, the feature representation of instances usually has big impact on the final performance; inspired by the recent deep learning studies, in this paper, we propose the DeepMIML network which exploits deep neural network formation to generate instance representation for MIML. The sub-concept learning component of the DeepMIML structure reserves the instance-label relation discovery ability of MIML algorithms; that is, it can automatically locating the key input patterns that trigger the labels. The effectiveness of DeepMIML network is validated by experiments on various domains of data.