Skip to main content

Sparse similarity-preserving hashing

Publication ,  Conference
Masci, J; Bronstein, AM; Bronstein, MM; Sprechmann, P; Sapiro, G
Published in: 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings
January 1, 2014

In recent years, a lot of attention has been devoted to efficient nearest neighbor search by means of similarity-preserving hashing. One of the plights of existing hashing techniques is the intrinsic trade-off between performance and computational complexity: while longer hash codes allow for lower false positive rates, it is very difficult to increase the embedding dimensionality without incurring in very high false negatives rates or prohibiting computational costs. In this paper, we propose a way to overcome this limitation by enforcing the hash codes to be sparse. Sparse high-dimensional codes enjoy from the low false positive rates typical of long hashes, while keeping the false negative rates similar to those of a shorter dense hashing scheme with equal number of degrees of freedom. We use a tailored feed-forward neural network for the hashing function. Extensive experimental evaluation involving visual and multimodal data shows the benefits of the proposed method.

Duke Scholars

Published In

2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings

Publication Date

January 1, 2014
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Masci, J., Bronstein, A. M., Bronstein, M. M., Sprechmann, P., & Sapiro, G. (2014). Sparse similarity-preserving hashing. In 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings.
Masci, J., A. M. Bronstein, M. M. Bronstein, P. Sprechmann, and G. Sapiro. “Sparse similarity-preserving hashing.” In 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings, 2014.
Masci J, Bronstein AM, Bronstein MM, Sprechmann P, Sapiro G. Sparse similarity-preserving hashing. In: 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings. 2014.
Masci, J., et al. “Sparse similarity-preserving hashing.” 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings, 2014.
Masci J, Bronstein AM, Bronstein MM, Sprechmann P, Sapiro G. Sparse similarity-preserving hashing. 2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings. 2014.

Published In

2nd International Conference on Learning Representations Iclr 2014 Conference Track Proceedings

Publication Date

January 1, 2014