Open AccessDeep hash: semantic similarity preserved hash scheme
Author(s) -
Feng Weiguo,
Jia Baozhi,
Zhu Ming
Publication year - 2014
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2014.2397
Subject(s) - hash function , computer science , equivalence (formal languages) , universal hashing , theoretical computer science , artificial intelligence , feature hashing , semantic similarity , scheme (mathematics) , similarity (geometry) , orthogonality , sigmoid function , algorithm , pattern recognition (psychology) , double hashing , mathematics , artificial neural network , hash table , discrete mathematics , mathematical analysis , geometry , computer security , image (mathematics)
A novel hashing scheme based on a deep network architecture is proposed to tackle semantic similarity problems. The proposed methodology utilises the ability of deep networks to learn nonlinear representations of the input features. The equivalence of the neuron layer and the sigmoid smoothed hash functions is introduced, and by incorporating the saturation and orthogonality regulariser, the final compact binary embeddings can be achieved. The experiments illustrate that the proposed scheme exhibits superior improvement compared with conventional hashing methods.