Tips and tricks for visual question answering: learnings from the 2017 challenge
Date
2018
Authors
Teney, D.
Anderson, P.
He, X.
Van Den Hengel, A.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp.4223-4232
Statement of Responsibility
Damien Teney, Peter Anderson, Xiaodong He, Anton van den Hengel
Conference Name
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (18 Jun 2018 - 23 Jun 2018 : Salt Lake City, USA)
Abstract
Deep Learning has had a transformative impact on Computer Vision, but for all of the success there is also a significant cost. This is that the models and procedures used are so complex and intertwined that it is often impossible to distinguish the impact of the individual design and engineering choices each model embodies. This ambiguity diverts progress in the field, and leads to a situation where developing a state-of-the-art model is as much an art as a science. As a step towards addressing this problem we present a massive exploration of the effects of the myriad architectural and hyperparameter choices that must be made in generating a state-of-the-art model. The model is of particular interest because it won the 2017 Visual Question Answering Challenge. We provide a detailed analysis of the impact of each choice on model performance, in the hope that it will inform others in developing models, but also that it might set a precedent that will accelerate scientific progress in the field.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2018 IEEE