Coordinating explicit and implicit knowledge for knowledge-based VQA

doi:10.1016/j.patcog.2024.110368

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Coordinating explicit and implicit knowledge for knowledge-based VQA
	Wang, Qunbo 1; Liu, Jing 1; Wu, Wenjun 2
刊名	PATTERN RECOGNITION
	2024-07-01
卷号	151 页码:9
关键词	Knowledge retrieval Pre -trained model Knowledge -based VQA
ISSN号	0031-3203
DOI	10.1016/j.patcog.2024.110368
通讯作者	Liu, Jing(jliu@nlpr.ia.ac.cn)
英文摘要	Pre -trained models often generate plausible looking statements that are factually incorrect because of the inaccurate implicit knowledge contained in the model's parameters. Related methods retrieve explicit knowledge from the external knowledge source to help improve the prediction performance and reliability. However, these methods often use weak training signals for the retriever, and require the model to make each prediction based on the retrieved knowledge, even when the retrieved knowledge is not reliable or the model can produce better prediction only using its implicit knowledge. Therefore, it is necessary to enable the pre -trained model to actively select more beneficial knowledge for producing better prediction. This work proposes a novel method to help the model to Coordinate Explicit and Implicit Knowledge (CEIK) for the knowledge -based visual question answering (VQA) task, which is an important direction of pre -trained models. Furthermore, a better training signal is proposed for the retriever according to whether the retrieved knowledge can correct the prediction. Experimental results demonstrate the effectiveness of our method.
资助项目	National Key R&D Program of China[2022ZD0118802] ; National Natural Science Foundation of China[62206279]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:001195942400001
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58044]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Liu, Jing
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100191, Peoples R China 2.Beihang Univ, Inst Artificial Intelligence, Beijing 100191, Peoples R China
推荐引用方式 GB/T 7714	Wang, Qunbo,Liu, Jing,Wu, Wenjun. Coordinating explicit and implicit knowledge for knowledge-based VQA[J]. PATTERN RECOGNITION,2024,151:9.
APA	Wang, Qunbo,Liu, Jing,&Wu, Wenjun.(2024).Coordinating explicit and implicit knowledge for knowledge-based VQA.PATTERN RECOGNITION,151,9.
MLA	Wang, Qunbo,et al."Coordinating explicit and implicit knowledge for knowledge-based VQA".PATTERN RECOGNITION 151(2024):9.