Mixture component identification and learning for visual recognition
2012 (English)In: Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VI, Springer, 2012, 115-128 p.Conference paper (Refereed)
The non-linear decision boundary between object and background classes - due to large intra-class variations - needs to be modelled by any classifier wishing to achieve good results. While a mixture of linear classifiers is capable of modelling this non-linearity, learning this mixture from weakly annotated data is non-trivial and is the paper's focus. Our approach is to identify the modes in the distribution of our positive examples by clustering, and to utilize this clustering in a latent SVM formulation to learn the mixture model. The clustering relies on a robust measure of visual similarity which suppresses uninformative clutter by using a novel representation based on the exemplar SVM. This subtle clustering of the data leads to learning better mixture models, as is demonstrated via extensive evaluations on Pascal VOC 2007. The final classifier, using a HOG representation of the global image patch, achieves performance comparable to the state-of-the-art while being more efficient at detection time.
Place, publisher, year, edition, pages
Springer, 2012. 115-128 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 7577
Decision boundary, Detection time, Image patches, Intra-class variation, Linear classifiers, Mixture components, Mixture model, Non-Linearity, Non-trivial, Positive examples, Visual recognition, Visual similarity, Weakly annotated data
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-106987DOI: 10.1007/978-3-642-33783-3_9ISI: 000342828800009ScopusID: 2-s2.0-84867892975ISBN: 978-364233782-6OAI: oai:DiVA.org:kth-106987DiVA: diva2:574329
12th European Conference on Computer Vision, ECCV 2012;Florence;7 October 2012 through 13 October 2012
FunderICT - The Next Generation
QC 201212072012-12-052012-12-052016-09-08Bibliographically approved