Deep Metric Learning
Benyamin Ghojogh, Mark Crowley, Fakhri O. Karray, Ali Ghodsi · 2023
It was mentioned in Chap. 11 that metric learning can be divided into spectral, probabilistic, and deep metric learning. Chapters 11 and 13 explained that both spectral and probabilistic metric learning methods use the generalized Mahalanobis distance, i.e., Eq. ( 11.53 ) in Chap. 11 , and learn the weight matrix in the metric. Deep metric learning, however, takes a different approach. Deep metric learning methods usually do not use a generalized Mahalanobis distance; instead, they learn an embedding space using a neural network. This chapter introduces and reviews deep metric learning methods.