Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Tips and tricks for visual question answering: learnings from the 2017 challenge
Author: Teney, D.
Anderson, P.
He, X.
Van Den Hengel, A.
Citation: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018 / pp.4223-4232
Publisher: IEEE
Issue Date: 2018
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781538664216
ISSN: 1063-6919
Conference Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (18 Jun 2018 - 23 Jun 2018 : Salt Lake City, USA)
Statement of
Damien Teney, Peter Anderson, Xiaodong He, Anton van den Hengel
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.
Rights: © 2018 IEEE
RMID: 0030084426
DOI: 10.1109/CVPR.2018.00444
Published version:
Appears in Collections:Australian Institute for Machine Learning publications

Files in This Item:
There are no files associated with this item.

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