• DOI:10.1109/CVPR42600.2020.00289
Corpus ID: 211532616

Auto-Encoding Twin-Bottleneck Hashing

@article{Shen2020AutoEncodingTH,
  title={Auto-Encoding Twin-Bottleneck Hashing},
  author={Yuming Shen and J. Qin and Jiaxin Chen and Mengyang Yu and Li Liu and F. Zhu and F. Shen and Ling Shao},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={2815-2824}
}

Yuming Shen, J. Qin, +5 authors Ling Shao

Published 2020

Computer Science

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Conventional unsupervised hashing methods usually take advantage of similarity graphs, which are either pre-computed in the high-dimensional space or obtained from random anchor points. On the one hand, existing methods uncouple the procedures of hash function learning and graph construction. On the other hand, graphs empirically built upon original data could introduce biased prior knowledge of data relevance, leading to sub-optimal retrieval performance. In this paper, we tackle the above… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed