TY - GEN
T1 - Active transfer learning for multi-view head-pose classification
AU - Yan, Yan
AU - Subramanian, Ramanathan
AU - Lanz, Oswald
AU - Sebe, Nicu
PY - 2012
Y1 - 2012
N2 - This paper describes an active transfer learning technique for multi-view head-pose classification. We combine transfer learning with active learning, where an active learner asks the domain expert to label the few most informative target samples for transfer learning. Employing adaptive multiple-kernel learning for head-pose classification from four low-resolution views, we show how active sampling enables more efficient learning with few examples. Experimental results confirm that active transfer learning produces 10% higher pose-classification accuracy over several competing transfer learning approaches.
AB - This paper describes an active transfer learning technique for multi-view head-pose classification. We combine transfer learning with active learning, where an active learner asks the domain expert to label the few most informative target samples for transfer learning. Employing adaptive multiple-kernel learning for head-pose classification from four low-resolution views, we show how active sampling enables more efficient learning with few examples. Experimental results confirm that active transfer learning produces 10% higher pose-classification accuracy over several competing transfer learning approaches.
UR - http://www.scopus.com/inward/record.url?scp=84874555387&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84874555387
SN - 9784990644109
T3 - Proceedings - International Conference on Pattern Recognition
SP - 1168
EP - 1171
BT - Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
T2 - 21st International Conference on Pattern Recognition, ICPR 2012
Y2 - 11 November 2012 through 15 November 2012
ER -