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
  • [21] Customer feature selection from high-dimensional bank direct marketing data for uplift modeling
    Jinping Hu
    Journal of Marketing Analytics, 2023, 11 : 160 - 171
  • [22] Customer feature selection from high-dimensional bank direct marketing data for uplift modeling
    Hu, Jinping
    JOURNAL OF MARKETING ANALYTICS, 2023, 11 (02) : 160 - 171
  • [23] Evaluation of bank transactions correctness with method of 2-dimensional projection of high-dimensional fuzzy membership functions
    Plucinski, M
    Piegat, A
    INTELLIGENT INFORMATION SYSTEMS, 2000, : 315 - 324
  • [24] High-dimensional data
    Geubbelmans, Melvin
    Rousseau, Axel-Jan
    Valkenborg, Dirk
    Burzykowski, Tomasz
    AMERICAN JOURNAL OF ORTHODONTICS AND DENTOFACIAL ORTHOPEDICS, 2023, 164 (03) : 453 - 456
  • [25] High-dimensional data
    Amaratunga, Dhammika
    Cabrera, Javier
    JOURNAL OF THE NATIONAL SCIENCE FOUNDATION OF SRI LANKA, 2016, 44 (01): : 3 - 9
  • [26] Multiple imputation for high-dimensional mixed incomplete continuous and binary data
    He, Ren
    Belin, Thomas
    STATISTICS IN MEDICINE, 2014, 33 (13) : 2251 - 2262
  • [27] State estimation from high-dimensional data
    Solo, V
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS: SENSOR ARRAY AND MULTICHANNEL SIGNAL PROCESSING SIGNAL PROCESSING THEORY AND METHODS, 2004, : 685 - 688
  • [28] Two-sample tests for sparse high-dimensional binary data
    Plunkett, Amanda
    Park, Junyong
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2017, 46 (22) : 11181 - 11193
  • [29] Two-sample mean vector projection test in high-dimensional data
    Huang, Caizhu
    Cui, Xia
    Pagui, Euloge Clovis Kenne
    COMPUTATIONAL STATISTICS, 2024, 39 (03) : 1061 - 1091
  • [30] Two-sample mean vector projection test in high-dimensional data
    Caizhu Huang
    Xia Cui
    Euloge Clovis Kenne Pagui
    Computational Statistics, 2024, 39 : 1061 - 1091