Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval
Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval
复制标题
DOI：
10.1609/aaai.v31i1.10719
复制
发表时间：
2017-02
影响因子：
6.5
通讯作者：
Erkun Yang;Cheng Deng;W. Liu;Xianglong Liu;D. Tao;Xinbo Gao
中科院分区：
文献类型：
--
作者：
Erkun Yang;Cheng Deng;W. Liu;Xianglong Liu;D. Tao;Xinbo Gao
由于存储成本低、查询速度快等优点，跨模式哈希算法近年来受到了广泛的关注。然而，现有的跨模态哈希方法由于直接利用手工特征或忽略了不同模态间的异构相关性而无法获得强大的哈希码，从而大大降低了检索性能。在本文中，我们提出了一种新的深度跨模态哈希方法，通过端到端深度学习架构生成紧凑的哈希码，该方法可以有效地捕获各种模态之间的内在关系。我们的体系结构集成了不同类型的两两约束，以鼓励分别来自内模态视图和多模态视图的哈希码的相似性。此外，在该体系结构中引入了额外的去相关约束，从而增强了每个哈希位的判别能力。大量的实验表明，我们提出的方法在两个跨模态检索数据集上产生了最先进的结果。
With benefits of low storage cost and fast query speed, cross-modal hashing has received considerable attention recently. However, almost all existing methods on cross-modal hashing cannot obtain powerful hash codes due to directly utilizing hand-crafted features or ignoring heterogeneous correlations across different modalities, which will greatly degrade the retrieval 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.