Goal-oriented visual question generation via intermediate rewards

Date

2018

Authors

Zhang, J.
Wu, Q.
Shen, C.
Zhang, J.
Lu, J.
van den Hengel, A.

Editors

Ferrari, V.
Hebert, M.
Sminchisescu, C.
Weiss, Y.

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Lecture Notes in Artificial Intelligence, 2018 / Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (ed./s), vol.Lecture Notes in Computer Science; vol. 11209, pp.189-204

Statement of Responsibility

Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu and Anton van den Hengel

Conference Name

15th European Conference on Computer Vision (ECCV 2018) (8 Sep 2018 - 14 Sep 2018 : Munich)

Abstract

Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of inane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard ‘Guesser’ identify a specific object in an image at a much higher success rate.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© Springer Nature Switzerland AG 2018

License

Grant ID

Call number

Persistent link to this record