FAST SCALABLE SUPERVISED HASHING

Xin Luo, Liqiang Nie, Xiangnan He
Ye Wu, Zhen-Duo Chen, Xin-Shun Xu

SIGIR 2018

 

FSSH

Three variants of FSSH:

  1. FSSH_os​

  2. FSSH_ts [code]

  3. FSSH_deep

As a byproduct, we have released the codes and parameter settings to facilitate other researchers. [code]

Baselines

  • Shallow models:

       KSH [code]

       SDH [code]

       FSDH  [code]

       TSH [code]

       LFH [code]

       COSDISH [code]

  • Deep models:       

       ​DSRH, DSCH, DRSCH, DPSH, VDSH, DTSH, and DSDH

Evaluation Metrics

Mean Average Precision (MAP)
Top-N Precision Curves  
Precision-Recall Curves 
(For all the three evaluation metrics, a larger value indicates the better retrieval performance.)

 

Acknowledgements

This work was partially supported by the Key Research and Development Program of Shandong Province (2016GGX101044), the National Natural Science Foundation of China (61573212, 61772310, 61702300, 61702302), and the Project of Thousand Youth Talents 2016. NExT research is supported by the National Research Foundation, Prime Minister's Office, Singapore under its IRC@SG Funding Initiative.

 

©2018 by FSSH. Proudly created with Wix.com

This site was designed with the
.com
website builder. Create your website today.
Start Now