Distribution Structure Learning Loss (DSLL) Based on Deep Metric Learning for Image Retrieval

Distribution Structure Learning Loss (DSLL) Based on Deep Metric Learning for Image Retrieval

The massive number of images demands highly efficient image retrieval tools. Deep distance metric learning (DDML) is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, which has achieved encouraging results. The loss function is crucial in DDM...

Full description

Bibliographic Details
Main Authors: Lili Fan, Hongwei Zhao, Haoyu Zhao, Pingping Liu, Huangshui Hu
Format: Article
Language:English
Published: MDPI AG 2019-11-01
Series:Entropy
Subjects:
deep metric learning
entropy weight
fine-tune network
image retrieval
structural preservation
structural ranking consistency
Online Access:https://www.mdpi.com/1099-4300/21/11/1121

Internet

https://www.mdpi.com/1099-4300/21/11/1121

Similar Items