Region of interest autoencoders with an application to pedestrian detection

Date

2017

Authors

Williams, J.
Carneiro, G.
Suter, D.

Editors

Guo, Y.
Li, H.
Cai, W.
Murshed, M.
Wang, Z.
Gao, J.
Feng, D.

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

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

Statement of Responsibility

Jerome Williams, Gustavo Carneiro, David Suter

Conference Name

International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017) (29 Nov 2017 - 1 Dec 2017 : Sydney, AUSTRALIA)

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

©2017 IEEE

License

Call number

Persistent link to this record