Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval
ErkunYang, 1 ChengDeng, 1 WeiLiu, 2 XianglongLiu, 3 DachengTao, 4 XinboGao1
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
With benefits of low storage cost and fast query speed, crossmodal hashing has received considerable attention recently. However,almostallexistingmethodsoncross-modalhashing cannot obtain powerful hash codes due to directly utilizing hand-crafted features or ignoring heterogeneous correlations acrossdifferentmodalities,whichwillgreatlydegradetheretrieval performance. In this paper, we propose a novel deep cross-modal hashing method to generate compact hash codes through an end-to-end deep learning architecture, which can effectively capture the intrinsic relationships between various modalities. Our architecture integrates different types of pairwise constraints to encourage the similarities of the hash codes from an intra-modal view and an inter-modal view, respectively. Moreover, additional decorrelation constraints are introduced to this architecture, thus enhancing the discriminative ability of each hash bit. Extensive experiments show that our proposed method yields state-of-the-art results on two cross-modal retrieval datasets.