Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Region of interest autoencoders with an application to pedestrian detection
Author: Williams, J.
Carneiro, G.
Suter, D.
Citation: Proceedings of the International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017), 2017 / Guo, Y., Li, H., Cai, W., Murshed, M., Wang, Z., Gao, J., Feng, D. (ed./s), vol.2017-December, pp.580-587
Publisher: IEEE
Publisher Place: Piscataway, NJ
Issue Date: 2017
ISBN: 1538628406
Conference Name: International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017) (29 Nov 2017 - 01 Dec 2017 : Sydney, AUSTRALIA)
Statement of
Jerome Williams, Gustavo Carneiro, David Suter
Abstract: We present the Region of Interest Autoencoder (ROIAE), a combined supervised and reconstruction model for the automatic visual detection of objects. More specifically, we augment the detection loss function with a reconstruction loss that targets only foreground examples. This allows us to exploit more effectively the information available in the sparsely populated foreground training data used in common detection problems. Using this training strategy we improve the accuracy of deep learning detection models. We carry out experiments on the Caltech-USA pedestrian detection dataset and demonstrate improvements over two supervised baselines. Our first experiment extends Fast R-CNN and achieves a 4% relative improvement in test accuracy over its purely supervised baseline. Our second experiment extends Region Proposal Networks, achieving a 14% relative improvement in test accuracy.
Rights: ©2017 IEEE
RMID: 0030085943
DOI: 10.1109/DICTA.2017.8227485
Grant ID:
Published version:
Appears in Collections:Computer Science 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.