Mar 7, 2018 · In this paper, we propose a replicable DML method, called Include and Exclude (IE) loss, to force the distance between a sample and its ...

May 17, 2018 · In this paper, we propose a powerful and replicable DML method, which enforces the mean inter-class distance larger than the intra-class ...

May 17, 2018 · Facing the more and more complex data, the deeper and wider CNNs tend to obtain better accuracies. Meanwhile, many troubles will show up, such ...

In this paper, we propose a replicable DML method, called Include and Exclude (IE) loss, to force the distance between a sample and its designated class center ...

Deep Metric Learning (DML), integrating deep learning with conventional metric learning, has set new records in many fields, especially in classification task.

Bowen Wu , Zhang-Ling Chen, Jun Wang, Hua-Ming Wu: Exponential discriminative metric embedding in deep learning. Neurocomputing 290: 108-120 (2018).

Exponential discriminative metric embedding in deep learning ; Journal: Neurocomputing, 2018, p. 108-120 ; Publisher: Elsevier BV ; Authors: Bowen Wu, Zhangling ...

Deep Metric Learning (DML), integrating deep learning with conventional metric learning, has set new records in many fields, especially in classification task.

Deep embedding learning aims to learn a distance metric for effective similarity measurement, which has achieved promising performance in various tasks.

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of ...