# Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval

27 Feb 2018Xuefei ZheShifeng ChenHong Yan

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for $L2$-normalized embedding space, i.e., a hyper-sphere... (read more)

PDF Abstract