首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
【24h】

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

机译:跨模态零散列哈希的属性导向网络

获取原文
获取原文并翻译 | 示例
           

摘要

Zero-shot hashing (ZSH) aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achieved by utilizing a semantic embedding space to transfer knowledge from seen domain to unseen domain. Existing efforts mainly focus on single-modal retrieval task, especially image-based image retrieval (IBIR). However, as a highlighted research topic in the field of hashing, cross-modal retrieval is more common in real-world applications. To address the cross-modal ZSH (CMZSH) retrieval task, we propose a novel attribute-guided network (AgNet), which can perform not only IBIR but also text-based image retrieval (TBIR). In particular, AgNet aligns different modal data into a semantically rich attribute space, which bridges the gap caused by modality heterogeneity and zero-shot setting. We also design an effective strategy that exploits the attribute to guide the generation of hash codes for image and text within the same network. Extensive experimental results on three benchmark data sets (AwA, SUN, and ImageNet) demonstrate the superiority of AgNet on both cross-modal and single-modal zero-shot image retrieval tasks.
机译:零散哈希(ZSH)旨在学习一种哈希模型,该模型仅由可见类别中的实例进行训练,但可以很好地生成未看见类别中的实例。通常,这是通过利用语义嵌入空间将知识从可见域转移到不可见域来实现的。现有的工作主要集中在单模式检索任务上,尤其是基于图像的图像检索(IBIR)。但是,作为哈希技术领域中一个突出的研究主题,交叉模式检索在实际应用中更为常见。为了解决跨模式ZSH(CMZSH)检索任务,我们提出了一种新颖的属性导向网络(AgNet),该网络不仅可以执行IBIR,而且还可以执行基于文本的图像检索(TBIR)。特别是,AgNet将不同的模态数据对齐到一个语义丰富的属性空间中,该属性空间弥合了由模态异质性和零触发设置引起的差距。我们还设计了一种有效的策略,该策略利用该属性来指导同一网络中图像和文本的哈希码生成。在三个基准数据集(AwA,SUN和ImageNet)上的大量实验结果证明了AgNet在跨模态和单模态零镜头图像检索任务上的优越性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号