A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition
Shihai Wang, Zelin Li · 2014
In the machine learning community, most algorithms proposed, particularly for inductive learning, are based entirely on one crucial assumption: that the training and test data points are drawn or generated from the exact same distribution. If this condition is not fully satisfied, most learning algorithms or models are corrupted. In this paper, we propose a new instance based transductive transfer learning method based on Boosting framework by using a distribution measure approach. There follows a detailed description of this distribution measure approach. Subsequently, we describe our boosting transfer learning method in detail and report its performance in facial expression recognition tasks.