arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1612.04844cs.CV
收藏

知识图谱在图像分类中的应用

The More You Know: Using Knowledge Graphs for Image Classification

Carnegie Mellon University(卡内基梅隆大学)

Kenneth Marino, Ruslan Salakhutdinov, Abhinav Gupta

摘要:

人类与现代基于学习的计算机视觉算法不同的一个特征是,人类能够获得关于世界的知识,并利用这些知识来推理视觉世界。人类可以了解物体的特征以及它们之间发生的关系,以学习各种各样的视觉概念,通常只有很少的例子。本文研究了知识图谱形式的结构化先验知识的使用,并表明使用这种知识可以提高图像分类的性能。我们建立在最近关于图的端到端学习的工作基础上,引入了图搜索神经网络,作为一种有效地将大型知识图谱整合到视觉分类管道中的方法。我们在一些实验中表明,我们的方法优于标准的神经网络基线多标签分类。

英文摘要:

One characteristic that sets humans apart from modern learning-based computer vision algorithms is the ability to acquire knowledge about the world and use that knowledge to reason about the visual world. Humans can learn about the characteristics of objects and the relationships that occur between them to learn a large variety of visual concepts, often with few examples. This paper investigates the use of structured prior knowledge in the form of knowledge graphs and shows that using this knowledge improves performance on image classification. We build on recent work on end-to-end learning on graphs, introducing the Graph Search Neural Network as a way of efficiently incorporating large knowledge graphs into a vision classification pipeline. We show in a number of experiments that our method outperforms standard neural network baselines for multi-label classification.

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。

↑