Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Sparse similarity-preserving hashing
Alex M. Bronstein, Guillermo Sapiro, Pablo Sprechmann, Jonathan Masci, Michael M. Bronstein
Dec 20, 2013 (modified: Dec 20, 2013)ICLR 2014 conference submissionreaders: everyone
Decision:submitted, no decision
Abstract: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 multi-modal data shows the benefits of the proposed method.
Enter your feedback below and we'll get back to you as soon as possible.