Distribution-Aware Hierarchical Weighting Method for Deep Metric Learning

Yinong Zhu; Yong Feng; Mingliang Zhou; Baohua Qiang; Leong Hou U; Jiajie Zhu

ICASSP 2021accepted0 citations

Distribution-Aware Hierarchical Weighting Method for Deep Metric Learning

Yinong Zhu, Yong Feng, Mingliang Zhou, Baohua Qiang, Leong Hou U, Jiajie Zhu

Abstract

In this paper, we propose distribution-aware hierarchical weighting (DHW) method for deep metric learning. First, we formulate the distributions of different classes according to the form of gaussian curves, and update distributions as the training process. Second, depending on the learnable distribution, we propose a loss function named distribution-aware loss with dynamic mining margins and hierarchical degrees of weights to make full use of samples. The experimental results show that our algorithm outperforms other state-of-the-art methods in terms of retrieval and clustering tasks. Code is available at https://github.com/zhuyinong1/DHW-master.

BibTeX

@inproceedings{icassp2021_distributionawar,
  title = {Distribution-Aware Hierarchical Weighting Method for Deep Metric Learning},
  author = {Yinong Zhu and Yong Feng and Mingliang Zhou and Baohua Qiang and Leong Hou U and Jiajie Zhu},
  booktitle = {ICASSP 2021},
  year = {2021}
}