Deep Discriminative Supervised Hashing via Siamese Network

Yang LI  Zhuang MIAO  Jiabao WANG  Yafei ZHANG  Hang LI  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.12   pp.3036-3040
Publication Date: 2017/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8126
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
hashing,  convolutional neural network,  siamese network,  image retrieval,  

Full Text: PDF>>
Buy this Article

The latest deep hashing methods perform hash codes learning and image feature learning simultaneously by using pairwise or triplet labels. However, generating all possible pairwise or triplet labels from the training dataset can quickly become intractable, where the majority of those samples may produce small costs, resulting in slow convergence. In this letter, we propose a novel deep discriminative supervised hashing method, called DDSH, which directly learns hash codes based on a new combined loss function. Compared to previous methods, our method can take full advantages of the annotated data in terms of pairwise similarity and image identities. Extensive experiments on standard benchmarks demonstrate that our method preserves the instance-level similarity and outperforms state-of-the-art deep hashing methods in the image retrieval application. Remarkably, our 16-bits binary representation can surpass the performance of existing 48-bits binary representation, which demonstrates that our method can effectively improve the speed and precision of large scale image retrieval systems.