loading
Papers

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Kenji Okuma ; Eric Brochu ; David G. Lowe and James J. Little

Affiliation: The University of British Columbia, Canada

ISBN: 978-989-8425-47-8

Keyword(s): Object localization, Active learning, Adaptive interface.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Data Mining ; Databases and Information Systems Integration ; Enterprise Information Systems ; Sensor Networks ; Signal Processing ; Soft Computing

Abstract: Thanks to large-scale image repositories, vast amounts of data for object recognition are now easily available. However, acquiring training labels for arbitrary objects still requires tedious and expensive human effort. This is particularly true for localization, where humans must not only provide labels, but also training windows in an image. We present an approach for reducing the number of labelled training instances required to train an object classifier and for assisting the user in specifying optimal object location windows. As part of this process, the algorithm performs localization to find bounding windows for training examples that are best aligned with the current classification function, which optimizes learning and reduces human effort. To test this approach, we introduce an active learning extension to a latent SVM learning algorithm. Our user interface for training object detectors employs real-time interaction with a human user. Our active learning system provides a me an performance improvement of 4.5% in the average precision over a state of the art detector on the PASCAL Visual Object Classes Challenge 2007 with an average of just 40 minutes of human labelling effort per class. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.233.217.242

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Okuma, K.; Brochu, E.; G. Lowe, D. and J. Little, J. (2011). AN ADAPTIVE INTERFACE FOR ACTIVE LOCALIZATION.In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 248-258. DOI: 10.5220/0003317302480258

@conference{visapp11,
author={Kenji Okuma. and Eric Brochu. and David G. Lowe. and James J. Little.},
title={AN ADAPTIVE INTERFACE FOR ACTIVE LOCALIZATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={248-258},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003317302480258},
isbn={978-989-8425-47-8},
}

TY - CONF

JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - AN ADAPTIVE INTERFACE FOR ACTIVE LOCALIZATION
SN - 978-989-8425-47-8
AU - Okuma, K.
AU - Brochu, E.
AU - G. Lowe, D.
AU - J. Little, J.
PY - 2011
SP - 248
EP - 258
DO - 10.5220/0003317302480258

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.