TY - GEN
T1 - Joint calibration of Ensemble of Exemplar SVMs
AU - Modolo, Davide
AU - Vezhnevets, Alexander
AU - Russakovsky, Olga
AU - Ferrari, Vittorio
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/14
Y1 - 2015/10/14
N2 - We present a method for calibrating the Ensemble of Exemplar SVMs model. Unlike the standard approach, which calibrates each SVM independently, our method optimizes their joint performance as an ensemble. We formulate joint calibration as a constrained optimization problem and devise an efficient optimization algorithm to find its global optimum. The algorithm dynamically discards parts of the solution space that cannot contain the optimum early on, making the optimization computationally feasible. We experiment with EE-SVM trained on state-of-the-art CNN descriptors. Results on the ILSVRC 2014 and PASCAL VOC 2007 datasets show that (i) our joint calibration procedure outperforms independent calibration on the task of classifying windows as belonging to an object class or not; and (ii) this improved window classifier leads to better performance on the object detection task.
AB - We present a method for calibrating the Ensemble of Exemplar SVMs model. Unlike the standard approach, which calibrates each SVM independently, our method optimizes their joint performance as an ensemble. We formulate joint calibration as a constrained optimization problem and devise an efficient optimization algorithm to find its global optimum. The algorithm dynamically discards parts of the solution space that cannot contain the optimum early on, making the optimization computationally feasible. We experiment with EE-SVM trained on state-of-the-art CNN descriptors. Results on the ILSVRC 2014 and PASCAL VOC 2007 datasets show that (i) our joint calibration procedure outperforms independent calibration on the task of classifying windows as belonging to an object class or not; and (ii) this improved window classifier leads to better performance on the object detection task.
UR - http://www.scopus.com/inward/record.url?scp=84959234729&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959234729&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2015.7299021
DO - 10.1109/CVPR.2015.7299021
M3 - Conference contribution
AN - SCOPUS:84959234729
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 3955
EP - 3963
BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PB - IEEE Computer Society
T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Y2 - 7 June 2015 through 12 June 2015
ER -