TY - GEN
T1 - Dynamic visual category learning
AU - Yeh, Tom
AU - Darrell, Trevor
PY - 2008
Y1 - 2008
N2 - Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories become modified or obsolete, or when categories are divided into subcategories or merged together. We develop novel methods for efficient incremental learning of SVM-based visual category classifiers to handle such dynamic tasks. Our method exploits previous classifier estimates to more efficiently learn the optimal parameters for the current set of training images and categories. We show empirically that for dynamic visual category tasks, our incremental learning methods are significantly faster than batch retraining.
AB - Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories become modified or obsolete, or when categories are divided into subcategories or merged together. We develop novel methods for efficient incremental learning of SVM-based visual category classifiers to handle such dynamic tasks. Our method exploits previous classifier estimates to more efficiently learn the optimal parameters for the current set of training images and categories. We show empirically that for dynamic visual category tasks, our incremental learning methods are significantly faster than batch retraining.
UR - http://www.scopus.com/inward/record.url?scp=51949111564&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2008.4587616
DO - 10.1109/CVPR.2008.4587616
M3 - Conference contribution
AN - SCOPUS:51949111564
SN - 9781424422432
T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Y2 - 23 June 2008 through 28 June 2008
ER -