CaltechAUTHORS
  A Caltech Library Service

Strong supervision from weak annotation: Interactive training of deformable part models

Branson, Steve and Perona, Pietro and Belongie, Serge (2011) Strong supervision from weak annotation: Interactive training of deformable part models. In: 2011 International Conference on Computer Vision. IEEE , Piscataway, NJ, pp. 1832-1839. ISBN 978-1-4577-1102-2. https://resolver.caltech.edu/CaltechAUTHORS:20170308-151509399

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170308-151509399

Abstract

We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semi-automate the labeling of a new example) and online learning (where a newly labeled example is used to update the current model parameters). This framework is scalable to large datasets and complex image models and is shown to have excellent theoretical and practical properties in terms of train time, optimality guarantees, and bounds on the amount of annotation effort per image. We apply this framework to part-based detection, and introduce a novel algorithm for interactive labeling of deformable part models. The labeling tool updates and displays in real-time the maximum likelihood location of all parts as the user clicks and drags the location of one or more parts. We demonstrate that the system can be used to efficiently and robustly train part and pose detectors on the CUB Birds-200-a challenging dataset of birds in unconstrained pose and environment.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/ICCV.2011.6126450DOIArticle
http://ieeexplore.ieee.org/document/6126450/PublisherArticle
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2011 IEEE. The authors thank Boris Babenko, Kristin Branson, and Peter Welinder for helpful discussions and feedback. Funding for this work was provided by NSF Grant AGS-0941760, ONR MURI Grant N00014-08-1-0638, ONR MURI Grant N00014-06-1-0734, and ONR MURI Grant 1015 G NA127.
Funders:
Funding AgencyGrant Number
NSFAGS-0941760
Office of Naval Research (ONR)N00014-08-1-0638
Office of Naval Research (ONR)N00014-06-1-0734
Office of Naval Research (ONR)1015 G NA127
Record Number:CaltechAUTHORS:20170308-151509399
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170308-151509399
Official Citation:S. Branson, P. Perona and S. Belongie, "Strong supervision from weak annotation: Interactive training of deformable part models," 2011 International Conference on Computer Vision, Barcelona, 2011, pp. 1832-1839. doi: 10.1109/ICCV.2011.6126450
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:74930
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:08 Mar 2017 23:32
Last Modified:03 Oct 2019 16:44

Repository Staff Only: item control page