Improve distance metric learning by learning positions of class centers

Kun Song, Lantian Chu, Junwei Han, Fakhri Karray

Keywords: distance metric learning, skewed mean function

Abstract: Deep metric learning aims at learning a deep neural network by letting similar samples have small distances while dissimilar samples have large distances. To achieve this goal, the current DML algorithms mainly focus on pulling similar samples in each class as closely as possible. However, pulling similar samples only considers the local distribution of the data samples and ignores the global distribution of the data set, i.e., the center positions of different classes. The global distribution helps the distance metric learning. For example, expanding the distance between centers can increase the discriminant ability of the extracted features. However, how to increase the distance between centers is a challenging task. In this paper, we design a genius function named the skewed mean function, which only considers the most considerable distances of a set of samples. So maximizing the value of the skewed mean function can make the largest distance larger. We also prove that the current energy functions used for uniformity regularization on centers are special cases of our skewed mean function. At last, we conduct extensive experiments to illustrate the superiority of our methods.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning