图 书 馆
基于标签关系图的大规模对象分类Large-Scale Object Classification using Label Relation Graphs |
|
| 课程网址: | http://videolectures.net/eccv2014_deng_relation_graphs/ |
| 主讲教师: | Jia Deng |
| 开课单位: | 密歇根州立大学 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  在本文中，我们研究如何以一种有原则的方式执行对象分类，该方法利用了现实世界标签的丰富结构。我们开发了一种新模型，该模型允许对标签之间的灵活关系进行编码。我们介绍了层次结构和排除（HEX）图，这是一种新的形式主义，可以捕获应用于同一对象的任何两个标签之间的语义关系：相互排斥，重叠和包含。然后，我们提供了严格的理论分析，以说明HEX图的属性，例如图结构的一致性，等效性和计算含义。接下来，我们提出了一种基于十六进制图的概率分类模型，并表明它具有许多理想的属性。最后，我们使用大规模基准评估我们的方法。实证结果表明，该模型可以通过利用标签关系显着改善对象分类。 |
| 课程简介: | In this paper we study how to perform object classification in a principled way that exploits the rich structure of real world labels. We develop a new model that allows encoding of flexible relations between labels. We introduce Hierarchy and Exclusion (HEX) graphs, a new formalism that captures semantic relations between any two labels applied to the same object: mutual exclusion, overlap and subsumption. We then provide rigorous theoretical analysis that illustrates properties of HEX graphs such as consistency, equivalence, and computational implications of the graph structure. Next, we propose a probabilistic classification model based on HEX graphs and show that it enjoys a number of desirable properties. Finally, we evaluate our method using a large-scale benchmark. Empirical results demonstrate that our model can significantly improve object classification by exploiting the label relations. |
| 关 键 词: | 标签关系; 对象分类; 概率分类模型 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-10-28：zyk |
| 最后编审: | 2020-10-29：zyk |
| 阅读次数: | 99 |