Joint Learning for Multi-class Object Detection

Hamidreza Odabai Fard, Mohamed Chaouch, Quoc-cuong Pham, Antoine Vacavant, Thierry Chateau

2014

Abstract

In practice, multiple objects in images are located by consecutively applying one detector for each class and taking the best confident score. In this work, we propose to show the advantage of grouping similar object classes into a hierarchical structure. While this approach has found interest in image classification, it is not analyzed for the object detection task. Each node in the hierarchy represents one decision line. All the decision lines are learned jointly using a novel problem formulation. Based on experiments using PASCAL VOC 2007 dataset, we show that our approach improves detection performance compared to a baseline approach.

Paper Citation

in Harvard Style

Odabai Fard H., Chaouch M., Pham Q., Vacavant A. and Chateau T. (2014). Joint Learning for Multi-class Object Detection . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 104-112. DOI: 10.5220/0004692401040112

in Bibtex Style

@conference{visapp14,
author={Hamidreza Odabai Fard and Mohamed Chaouch and Quoc-cuong Pham and Antoine Vacavant and Thierry Chateau},
title={Joint Learning for Multi-class Object Detection},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={104-112},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004692401040112},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Joint Learning for Multi-class Object Detection
SN - 978-989-758-004-8
AU - Odabai Fard H.
AU - Chaouch M.
AU - Pham Q.
AU - Vacavant A.
AU - Chateau T.
PY - 2014
SP - 104
EP - 112
DO - 10.5220/0004692401040112