Object detection meets knowledge graphs

• Main Authors: FANG, Yuan, KUAN, Kingsley, LIN, Jie, TAN, Cheston, CHANDRASEKHAR, Vijay
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Machine Learning; Knowledge-based Learning; Robotics and Vision; Vision and Perception; Artificial intelligence; Deep neural networks; Object recognition; Optimization; Semantics; Databases and Information Systems; Graphics and Human Computer Interfaces; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/4067; https://ink.library.smu.edu.sg/context/sis_research/article/5070/viewcontent/0230.pdf
• Institution: Singapore Management University

Object detection in images is a crucial task in computer vision, with important applications ranging from security surveillance to autonomous vehicles. Existing state-of-the-art algorithms, including deep neural networks, only focus on utilizing features within an image itself, largely neglecting the vast amount of background knowledge about the real world. In this paper, we propose a novel framework of knowledge-aware object detection, which enables the integration of external knowledge such as knowledge graphs into any object detection algorithm. The framework employs the notion of semantic consistency to quantify and generalize knowledge, which improves object detection through a re-optimization process to achieve better consistency with background knowledge. Finally, empirical evaluation on two benchmark datasets show that our approach can significantly increase recall by up to 6.3 points without compromising mean average precision, when compared to the state-of-the-art baseline.