Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing

被引:88
|
作者
Hu, Hengtong [1 ,2 ]
Xie, Lingxi [3 ]
Hong, Richang [1 ,2 ]
Tian, Qi [3 ]
机构
[1] Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei, Peoples R China
[2] Hefei Univ Technol, Key Lab Knowledge Engn Big Data, Hefei, Peoples R China
[3] Huawei Inc, Shenzhen, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/CVPR42600.2020.00319
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main frameworks for CMH, differing from each other in whether semantic supervision is required. Compared to the unsupervised methods, the supervised methods often enjoy more accurate results, but require much heavier labors in data annotation. In this paper, we propose a novel approach that enables guiding a supervised method using outputs produced by an unsupervised method. Specifically, we make use of teacher-student optimization for propagating knowledge. Experiments are performed on two popular CMH benchmarks, i.e., the MIRFlickr and NUS-WIDE datasets. Our approach outperforms all existing unsupervised methods by a large margin.
引用
收藏
页码:3120 / 3129
页数:10
相关论文
共 50 条
  • [1] Unsupervised Deep Cross-Modal Hashing by Knowledge Distillation for Large-scale Cross-modal Retrieval
    Li, Mingyong
    Wang, Hongya
    [J]. PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR '21), 2021, : 183 - 191
  • [2] Learning From Expert: Vision-Language Knowledge Distillation for Unsupervised Cross-Modal Hashing Retrieval
    Sun, Lina
    Li, Yewen
    Dong, Yumin
    [J]. PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023, 2023, : 499 - 507
  • [3] Semi-Supervised Knowledge Distillation for Cross-Modal Hashing
    Su, Mingyue
    Gu, Guanghua
    Ren, Xianlong
    Fu, Hao
    Zhao, Yao
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 662 - 675
  • [4] Unsupervised Contrastive Cross-Modal Hashing
    Hu, Peng
    Zhu, Hongyuan
    Lin, Jie
    Peng, Dezhong
    Zhao, Yin-Ping
    Peng, Xi
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (03) : 3877 - 3889
  • [5] Completely Unsupervised Cross-Modal Hashing
    Duan, Jiasheng
    Zhang, Pengfei
    Huang, Zi
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2020), PT I, 2020, 12112 : 178 - 194
  • [6] Unsupervised Generative Adversarial Cross-Modal Hashing
    Zhang, Jian
    Peng, Yuxin
    Yuan, Mingkuan
    [J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 539 - 546
  • [7] Unsupervised Deep Fusion Cross-modal Hashing
    Huang, Jiaming
    Min, Chen
    Jing, Liping
    [J]. ICMI'19: PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2019, : 358 - 366
  • [8] Unsupervised Cross-Modal Hashing with Soft Constraint
    Zhou, Yuxuan
    Li, Yaoxian
    Liu, Rui
    Hao, Lingyun
    Sun, Yuanliang
    [J]. ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT II, 2018, 10736 : 756 - 765
  • [9] Unsupervised Multi-modal Hashing for Cross-Modal Retrieval
    Yu, Jun
    Wu, Xiao-Jun
    Zhang, Donglin
    [J]. COGNITIVE COMPUTATION, 2022, 14 (03) : 1159 - 1171
  • [10] Unsupervised Multi-modal Hashing for Cross-Modal Retrieval
    Jun Yu
    Xiao-Jun Wu
    Donglin Zhang
    [J]. Cognitive Computation, 2022, 14 : 1159 - 1171