Enhanced Deep Discrete Hashing with semantic-visual similarity for image retrieval

被引:13
作者
Yang, Zhan [1 ,2 ,3 ]
Yang, Liu [1 ]
Huang, Wenti [1 ,2 ]
Sun, Longzhi [1 ,2 ]
Long, Jun [2 ,3 ]
机构
[1] Cent South Univ, Sch Comp Sci & Engn, Changsha 410000, Hunan, Peoples R China
[2] Network Resources Management & Trust Evaluat Key, Changsha 410000, Hunan, Peoples R China
[3] Cent South Univ, Big Data Inst, Changsha 410083, Peoples R China
基金
中国国家自然科学基金;
关键词
Image retrieval; Deep hashing; Semantic-visual continuous similarity; Supervised learning; Convolutional neural networks; QUANTIZATION; ALGORITHMS; NEIGHBOR;
D O I
10.1016/j.ipm.2021.102648
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Hashing has been shown to be successful in a number of Approximate Nearest Neighbor (ANN) domains, ranging from medicine, computer vision to information retrieval. However, current deep hashing methods either ignore both rich information of labels and visual linkages of image pairs, or leverage relaxation-based algorithms to address discrete problems, resulting in a large information loss. To address the aforementioned problems, in this paper, we propose an Enhanced Deep Discrete Hashing (EDDH) method to leverage both label embedding and semantic-visual similarity to learn the compact hash codes. In EDDH, the discriminative capability of hash codes is enhanced by a distribution-based continuous semantic-visual similarity matrix, where not only the margin between the positive pairs and negative pairs is expanded, but also the visual linkages between image pairs is considered. Specifically, the semantic-visual continuous similarity matrix is constructed by analyzing the asymmetric generalized Gaussian distribution of the visual linkages between pairs with label consideration. Besides, in order to achieve an efficient hash learning framework, EDDH employs an asymmetric real-valued learning structure to learn the compact hash codes. In addition, we develop a fast discrete optimization algorithm, which can directly generate discrete binary codes in single step, and introduce an intermediate term before iterations to avoid the problems caused by directly the use of large semantic-visual similarity matrix, which results in a significant reduction in the computational overhead. Finally, we conducted extensive experiments on three datasets to show that EDDH has a significantly enhanced performance compared to the compared state-of-the-art baselines.
引用
收藏
页数:15
相关论文
共 61 条
  • [1] Andoni A, 2006, ANN IEEE SYMP FOUND, P459
  • [2] [Anonymous], 2009, CIVR
  • [3] Distributed optimization and statistical learning via the alternating direction method of multipliers
    Boyd S.
    Parikh N.
    Chu E.
    Peleato B.
    Eckstein J.
    [J]. Foundations and Trends in Machine Learning, 2010, 3 (01): : 1 - 122
  • [4] Cao Y, 2016, AAAI CONF ARTIF INTE, P3457
  • [5] Deep Priority Hashing
    Cao, Zhangjie
    Sun, Ziping
    Long, Mingsheng
    Wang, Jianmin
    Yu, Philip S.
    [J]. PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 1653 - 1661
  • [6] Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings
    Carvalho, Micael
    Cadene, Remi
    Picard, David
    Soulier, Laure
    Thome, Nicolas
    Cord, Matthieu
    [J]. ACM/SIGIR PROCEEDINGS 2018, 2018, : 35 - 44
  • [7] node2hash: Graph aware deep semantic text hashing
    Chaidaroon, Suthee
    Park, Dae Hoon
    Chang, Yi
    Fang, Yi
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2020, 57 (06)
  • [8] The devil is in the details: an evaluation of recent feature encoding methods
    Chatfield, Ken
    Lempitsky, Victor
    Vedaldi, Andrea
    Zisserman, Andrew
    [J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,
  • [9] Deep Supervised Hashing with Anchor Graph
    Chen, Yudong
    Lai, Zhihui
    Ding, Yujuan
    Lin, Kaiyi
    Wong, Wai Keung
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9795 - 9803
  • [10] Histograms of oriented gradients for human detection
    Dalal, N
    Triggs, B
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 886 - 893