Cross-modal Zero-shot Hashing

被引:13
|
作者
Liu, Xuanwu [1 ]
Li, Zhao [2 ]
Wang, Jun [1 ]
Yu, Guoxian [1 ,3 ]
Domeniconi, Carlotta [4 ]
Zhang, Xiangliang [3 ]
机构
[1] Southwest Univ, Coll Comp & Informat Sci, Chongqing, Peoples R China
[2] Alibaba Grp, Hangzhou, Peoples R China
[3] King Abdullah Univ Sci & Technol, CEMSE, Thuwal, Saudi Arabia
[4] George Mason Univ, Dept Comp Sci, Fairfax, VA 22030 USA
来源
2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019) | 2019年
关键词
Zero-shot Learning; Cross-modal Hashing; Labeled and Unlabeled Data; Deep Learning;
D O I
10.1109/ICDM.2019.00055
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.
引用
收藏
页码:449 / 458
页数:10
相关论文
共 50 条
  • [1] CHOP: An orthogonal hashing method for zero-shot cross-modal retrieval
    Yuan, Xu
    Wang, Guangze
    Chen, Zhikui
    Zhong, Fangming
    PATTERN RECOGNITION LETTERS, 2021, 145 : 247 - 253
  • [2] Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
    Ji, Zhong
    Sun, Yuxin
    Yu, Yunlong
    Pang, Yanwei
    Han, Jungong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (01) : 321 - 330
  • [3] Discrete asymmetric zero-shot hashing with application to cross-modal retrieval
    Shu, Zhenqiu
    Yong, Kailing
    Yu, Jun
    Gao, Shengxiang
    Mao, Cunli
    Yu, Zhengtao
    NEUROCOMPUTING, 2022, 511 : 366 - 379
  • [4] Zero-shot discrete hashing with adaptive class correlation for cross-modal retrieval
    Yong, Kailing
    Shu, Zhenqiu
    Yu, Jun
    Yu, Zhengtao
    KNOWLEDGE-BASED SYSTEMS, 2024, 295
  • [5] Unpaired robust hashing with noisy labels for zero-shot cross-modal retrieval
    Yong, Kailing
    Shu, Zhenqiu
    Yu, Zhengtao
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
  • [6] Robust zero-shot discrete hashing with noisy labels for cross-modal retrieval
    Yong, Kailing
    Shu, Zhenqiu
    Wang, Hongbin
    Yu, Zhengtao
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024,
  • [7] Attribute-Guided Multiple Instance Hashing Network for Cross-Modal Zero-Shot Hashing
    Song, Lingyun
    Shang, Xuequn
    Yang, Chen
    Sun, Mingxuan
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 5305 - 5318
  • [8] Generalized Zero-Shot Cross-Modal Retrieval
    Dutta, Titir
    Biswas, Soma
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (12) : 5953 - 5962
  • [9] Two-stage zero-shot sparse hashing with missing labels for cross-modal retrieval
    Yong, Kailing
    Shu, Zhenqiu
    Wang, Hongbin
    Yu, Zhengtao
    PATTERN RECOGNITION, 2024, 155
  • [10] A Cross-Modal Alignment for Zero-Shot Image Classification
    Wu, Lu
    Wu, Chenyu
    Guo, Han
    Zhao, Zhihao
    IEEE ACCESS, 2023, 11 : 9067 - 9073