Integrating Knowledge and Reasoning in Image Understanding
Integrating Knowledge and Reasoning in Image Understanding
复制标题
DOI：
10.24963/ijcai.2019/873
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Somak Aditya;Yezhou Yang;Chitta Baral
中科院分区：
文献类型：
--
作者：
Somak Aditya;Yezhou Yang;Chitta Baral
基于深度学习的数据驱动方法已成功地应用于各种图像理解应用程序，从对象识别，语义分割到视觉问题答案。但是，缺乏知识整合以及使用这些方法的高级推理能力仍然构成障碍。在这项工作中，我们简要调查了一些代表性的推理机制，知识整合方法及其相应的图像理解应用程序由各个研究人员开发的应用程序，从各种角度解决了问题。此外，我们讨论了将外部知识与神经网络融为一体的关键努力。从这些努力中获取线索，我们通过讨论提高推理能力的潜在途径来得出结论。
Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge integration as well as higher-level reasoning capabilities with the methods still pose a hindrance. In this work, we present a brief survey of a few representative reasoning mechanisms, knowledge integration methods and their corresponding image understanding applications developed by various groups of researchers, approaching the problem from a variety of angles. Furthermore, we discuss upon key efforts on integrating external knowledge with neural networks. Taking cues from these efforts, we conclude by discussing potential pathways to improve reasoning capabilities.