Multi-kernel metric learning for person re-identification
Muhammad Adnan Syed, Jianbin Jiao · 2016
In this paper, we propose a new Multi-kernel Metric Learning (MKML) approach to enhance the performance of person re-identification using adaptive weighted Multi-kernel. The intuition behind our approach is that different features, i.e., low-level and middle-level features, have different nature and thus discriminating capability, utilizing different kernels could map these features into sub-spaces, which helps to improve the discrimination among features. The kernels are combined with an adaptive weighting strategy to get an efficient kernel space. The Fisher Discriminant Analysis (FDA) is used to learn the metric in the learned weighted kernels space that enhances the robustness of metric to discriminate among classes. Experiments on two challenging person reidentification datasets, i.e., VIPeR and CUHK01, demonstrated that our approach is effective.