Active transfer learning for multi-view head-pose classification

Yan Yan, Subramanian Ramanathan, Oswald Lanz, Nicu Sebe

Abstract: 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.