Open AccessDeep supervised hashing network with integrated regularisation
Author(s) -
Liao Jianxin,
Li Baoran,
Yang Di,
Wang Jingyu,
Qi Qi,
Wang Jing
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.6644
Subject(s) - hash function , binary code , computer science , image retrieval , artificial intelligence , similarity (geometry) , pattern recognition (psychology) , hash table , representation (politics) , binary number , feature (linguistics) , feature hashing , image (mathematics) , data mining , mathematics , double hashing , linguistics , philosophy , computer security , arithmetic , politics , political science , law
Hashing has been widely deployed to approximate nearest neighbour search for large‐scale multimedia retrieval tasks due to storage and retrieval efficiency. State‐of‐the‐art supervised hashing methods for image retrieval construct deep structures to simultaneously learn image representation and generate good hash codes, and the key step among them is simultaneously learned feature representation and binary hash code. Existing methods use similarity and regularity loss to train deep hashing systems, but these two functions usually work together but not cooperative, which may lead to inadequate performance of the whole system. In this study, a new method for training deep hashing system to learn compact binary codes is presented. The deep supervised hashing network with integrated regularisation (DSHIR) system develop the zero division restriction as a new part of the loss function, which settles the problem of cooperatively guiding the system generate similarity preserving binary codes. DSHIR system also modifies the similarity handling loss to better extract features from image data, which promotes the performance compared to existing end‐to‐end deep hashing systems. Experiments show that DSHIR yields about 10 per cent higher mean average precision on CIFAR‐10 dataset, and also promote on other evaluation indexes compared with state‐of‐the‐art systems.