CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Answer Distillation for Visual Question Answering
Fang, Zhiwei1,2; Liu, Jing1; Tang, Qu1; Li, Yong3; Lu, Hanqing1
2019-05
Conference NameAsian Conference on Computer Vision
Conference Date2018.12
Conference PlacePerth, Australia
Abstract

Answering open-ended questions in Visual Question Answering (VQA) is a challenging task. As the answers are totally free-form, the answer space for open-ended questions is in nite in theory. This increases the diffculty for algorithms to predict the correct answers. In this paper, we propose a method named answer distillation to decrease the scale of answer space and limit the correct result into a small set of answer candidates. Speci cally, we design a two-stage architecture to answer a question: First, we develop an answer distillation network to distill the answers, converting an open-ended question to a multiple-choice one with a short list of answer candidates. Then, we make full use of the knowledge from the answer candidates to guide the visual attention and re ne the prediction results. Extensive experiments are conducted to validate the effiectiveness of our answer distillation architecture. The results show that our method can effiectively compress the answer space and improve the accuracy on open-ended task, providing a new state-of-the-art performance on COCO-VQA dataset.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23599
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorLiu, Jing
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Business Growth BU, JD.com
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Fang, Zhiwei,Liu, Jing,Tang, Qu,et al. Answer Distillation for Visual Question Answering[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
Answer Distillation (2077KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fang, Zhiwei]'s Articles
[Liu, Jing]'s Articles
[Tang, Qu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fang, Zhiwei]'s Articles
[Liu, Jing]'s Articles
[Tang, Qu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fang, Zhiwei]'s Articles
[Liu, Jing]'s Articles
[Tang, Qu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Answer Distillation for Visual Question Answering.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.