Instance-weighted Transfer Learning of Active Appearance Models

Daniel Haase, Erik Rodner, Joachim Denzler; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1426-1433


There has been a lot of work on face modeling, analysis, and landmark detection, with Active Appearance Models being one of the most successful techniques. A major drawback of these models is the large number of detailed annotated training examples needed for learning. Therefore, we present a transfer learning method that is able to learn from related training data using an instance-weighted transfer technique. Our method is derived using a generalization of importance sampling and in contrast to previous work we explicitly try to tackle the transfer already during learning instead of adapting the fitting process. In our studied application of face landmark detection, we efficiently transfer facial expressions from other human individuals and are thus able to learn a precise face Active Appearance Model only from neutral faces of a single individual. Our approach is evaluated on two common face datasets and outperforms previous transfer methods.

Related Material

author = {Haase, Daniel and Rodner, Erik and Denzler, Joachim},
title = {Instance-weighted Transfer Learning of Active Appearance Models},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}