Transformed Anti-Sparse Hashing
Zhangyang Wang, Ji Liu, Shuai Huang, Xinchao Wang and Shiyu Chang
Abstract
Anti-sparse representation was recently considered for unsupervised hashing, due to
its remarkable robustness to the binary quantization error. We relax the existing spread
property [4, 22] for anti-sparse solutions, to a new Relaxed Spread Property (RSP) that
demands milder conditions. We then propose a novel Transformed Anti-Sparse Hashing
(TASH) model to overcome several major bottlenecks, that have significantly limited the
effectiveness of anti-sparse hashing models. TASH jointly learns a dimension-reduction
transform, a dictionary and the anti-sparse representations in a unified formulation.
Session
Posters
Files
Paper (PDF)
DOI
10.5244/C.31.37
https://dx.doi.org/10.5244/C.31.37
Citation
Zhangyang Wang, Ji Liu, Shuai Huang, Xinchao Wang and Shiyu Chang. Transformed Anti-Sparse Hashing. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 37.1-37.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_37,
title={Transformed Anti-Sparse Hashing},
author={Zhangyang Wang, Ji Liu, Shuai Huang, Xinchao Wang and Shiyu Chang},
year={2017},
month={September},
pages={37.1-37.12},
articleno={37},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.37},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.37}
}