Name
Abstract | ||
|---|---|---|
Similarity-preserving hashing is a widely used method for nearest neighbor search in large-scale image retrieval. Recently, supervised hashing methods are appealing in that they learn compact hash codes with fewer bits by incorporating supervised information. In this paper, we propose a new two-stage supervised hashing methods which decomposes the hash learning process into a stage of learning approximate hash codes followed by a stage of learning hash functions. In the first stage, we propose a margin-based objective to find approximate hash codes such that a pair of hash codes associating to a pair of similar (dissimilar) images has sufficiently small (large) Hamming distance. This objective results in a challenging optimization problem. We develop a coordinate descent algorithm to efficiently solve this optimization problem. In the second stage, we use convolutional neural networks to learn hash functions. We conduct extensive evaluations on several benchmark datasets with different kinds of images. The results show that the proposed margin-based hashing method has substantial improvement upon the state-of-the-art supervised or unsupervised hashing methods. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1016/j.neucom.2016.07.024 | Neurocomputing |
Keywords | Field | DocType |
Deep learning,Image retrieval,Image hashing,Neural network,Optimization algorithm | Double hashing,Computer science,Universal hashing,Feature hashing,Theoretical computer science,Artificial intelligence,Linear hashing,Locality-sensitive hashing,Pattern recognition,Hash function,Dynamic perfect hashing,Machine learning,Hash table | Journal |
Volume | Issue | ISSN |
214 | C | 0925-2312 |
Citations | PageRank | References |
3 | 0.39 | 10 |
Authors | ||
5 | ||