Projection Bank: From High-dimensional Data to Medium-length Binary Codes

被引:14
|
作者
Liu, Li [1 ]
Yu, Mengyang [1 ]
Shao, Ling [1 ]
机构
[1] Northumbria Univ, Dept Comp Sci & Digital Technol, Newcastle Upon Tyne NE1 8ST, Tyne & Wear, England
来源
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年
关键词
D O I
10.1109/ICCV.2015.323
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, very high-dimensional feature representations, e.g., Fisher Vector, have achieved excellent performance for visual recognition and retrieval. However, these lengthy representations always cause extremely heavy computational and storage costs and even become unfeasible in some large-scale applications. A few existing techniques can transfer very high-dimensional data into binary codes, but they still require the reduced code length to be relatively long to maintain acceptable accuracies. To target a better balance between computational efficiency and accuracies, in this paper, we propose a novel embedding method called Binary Projection Bank (BPB), which can effectively reduce the very high-dimensional representations to medium-dimensional binary codes without sacrificing accuracies. Instead of using conventional single linear or bilinear projections, the proposed method learns a bank of small projections via the max-margin constraint to optimally preserve the intrinsic data similarity. We have systematically evaluated the proposed method on three datasets: Flickr 1M, ILSVR2010 and UCF101, showing competitive retrieval and recognition accuracies compared with state-of-the-art approaches, but with a significantly smaller memory footprint and lower coding complexity.
引用
收藏
页码:2821 / 2829
页数:9
相关论文
共 50 条
  • [41] A Bipartite Graph Framework for Summarizing High-Dimensional Binary, Categorical and Numeric Data
    Chen, Guanhua
    Ma, Xiuli
    Yang, Dongqing
    Tang, Shiwei
    Meng Shuai
    SCIENTIFIC AND STATISTICAL DATABASE MANAGEMENT, PROCEEDINGS, 2009, 5566 : 580 - +
  • [42] High-dimensional data visualization
    Tang, Lin
    NATURE METHODS, 2020, 17 (02) : 129 - 129
  • [43] Calibrating an Ice Sheet Model Using High-Dimensional Binary Spatial Data
    Chang, Won
    Haran, Murali
    Applegate, Patrick
    Pollard, David
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2016, 111 (513) : 57 - 72
  • [44] Differentially Private High-Dimensional Binary Data Publication via Attribute Segmentation
    Hong J.
    Wu Y.
    Cai J.
    Sun L.
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2022, 59 (01): : 182 - 196
  • [45] High-dimensional data visualization
    Lin Tang
    Nature Methods, 2020, 17 : 129 - 129
  • [46] High-dimensional Data Cubes
    John, Sachin Basil
    Koch, Christoph
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2022, 15 (13): : 3828 - 3840
  • [47] Modeling High-Dimensional Data
    Vempala, Santosh S.
    COMMUNICATIONS OF THE ACM, 2012, 55 (02) : 112 - 112
  • [48] Learning high-dimensional data
    Verleysen, M
    LIMITATIONS AND FUTURE TRENDS IN NEURAL COMPUTATION, 2003, 186 : 141 - 162
  • [49] A telescope for high-dimensional data
    Shneiderman, B
    COMPUTING IN SCIENCE & ENGINEERING, 2006, 8 (02) : 48 - 53
  • [50] Clustering High-Dimensional Data
    Masulli, Francesco
    Rovetta, Stefano
    CLUSTERING HIGH-DIMENSIONAL DATA, CHDD 2012, 2015, 7627 : 1 - 13