| 摘要: |
| 跨模态哈希通过将不同模态的数据映射为同一空间中更紧凑的哈希码，可以大大提升跨模态检索的效率.然而现有跨模态哈希方法通常使用二元相似性矩阵，不能准确描述样本间的语义相似关系，并且存在平方复杂度问题.为了更好地挖掘数据间的语义相似关系，提出了一个基于标记增强的离散跨模态哈希方法.首先借助迁移学习的先验知识生成样本的标记分布，然后通过标记分布构建描述度更强的语义相似性矩阵，再通过一个高效的离散优化算法生成哈希码，避免了量化误差问题.最后，在两个基准数据集上的实验结果验证了所提方法在跨模态检索任务上的有效性. |
| 关键词: 跨模态检索 哈希 标记增强 迁移学习 离散优化 |
| DOI：10.13328/j.cnki.jos.006536 |
| 分类号:TP391 |
| 基金项目:国家自然科学基金（62172256，61872428，61991411）；山东省重点研发计划（2019JZZY010127）；山东省自然科学基金（ZR2019ZD06，ZR2020QF036） |
|
| Label Enhancement Based Discrete Cross-modal Hashing Method |
|
WANG Yong-Xin1,2, TIAN Jie-Ru2, CHEN Zhen-Duo2, LUO Xin2, XU Xin-Shun2
|
|
1.School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101, China;2.School of Software, Shandong University, Jinan 250101, China
|
| Abstract: |
| Cross-modal hashing can greatly improve the efficiency of cross-modal retrieval by mapping data of different modalities into more compact hash codes. Nevertheless, existing cross-modal hashing methods usually use a binary similarity matrix, which cannot accurately describe the semantic similarity relationships between samples and suffer from the squared complexity problem. In order to better mine the semantic similarity relationships of data, this study presents a label enhancement based discrete cross-modal hashing method (LEDCH). It first leverages the prior knowledge of transfer learning to generate the label distribution of samples, then constructs a stronger similarity matrix through the label distribution, and generates the hash codes by an efficient discrete optimization algorithm with a small quantization error. Finally, experimental results on two benchmark datasets validate the effectiveness of the proposed method on cross-modal retrieval tasks. |
| Key words: cross-modal retrieval hashing label enhancement transfer learning discrete optimization |
