Learning by Asking Questions

Ishan Misra, Ross Girshick, Rob Fergus, Martial Hebert, Abhinav Gupta, Laurens van der Maaten; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 11-20

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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Misra_2018_CVPR,
author = {Misra, Ishan and Girshick, Ross and Fergus, Rob and Hebert, Martial and Gupta, Abhinav and van der Maaten, Laurens},
title = {Learning by Asking Questions},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}