Paper Info
Title
Learning by Asking Questions
Abstract
We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task. LBA differs from standard VQA training in that most questions are not observed during training time, and the learner must ask questions it wants answers to. Thus, LBA more closely mimics natural learning and has the potential to be more data-efficient than the traditional VQA setting. We present a model that performs LBA on the CLEVR dataset, and show that it automatically discovers an easy-to-hard curriculum when learning interactively from an oracle. Our LBA generated data consistently matches or outperforms the CLEVR train data and is more sample efficient. We also show that our model asks questions that generalize to state-of-the-art VQA models and to novel test time distributions.
Year
DOI
Venue
2018
10.1109/CVPR.2018.00009
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Keywords
DocType
Volume
state-of-the-art VQA models,test time distributions,interactive learning framework,testing,LBA differs,standard VQA training,training time,data-efficient,CLEVR train data,LBA,VQA setting,visual question answering
Conference
abs/1712.01238
ISSN
ISBN
Citations 
1063-6919
978-1-5386-6421-6
8
PageRank 
References 
Authors
0.45
35
6
Name
Order
Citations
PageRank
Ishan Misra120112.69
Ross B. Girshick221921927.22
Robert Fergus311214735.18
Martial Hebert4112771146.89
Abhinav Gupta54692234.95
van der maaten676348.75