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
  • [1] EFFICIENT BINARY CODES FOR EXTREMELY HIGH-DIMENSIONAL DATA
    Lin, Tsung-Yu
    Liu, Tyng-Luh
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 2212 - 2216
  • [2] Fried Binary Embedding: From High-Dimensional Visual Features to High-Dimensional Binary Codes
    Hong, Weixiang
    Yuan, Junsong
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (10) : 4825 - 4837
  • [3] Learning Binary Codes for High-Dimensional Data Using Bilinear Projections
    Gong, Yunchao
    Kumar, Sanjiv
    Rowley, Henry A.
    Lazebnik, Svetlana
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 484 - 491
  • [4] Tensorized Projection for High-Dimensional Binary Embedding
    Hong, Weixiang
    Meng, Jingjing
    Yuan, Junsong
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 69 - 76
  • [5] Sparse Projections for High-Dimensional Binary Codes
    Xia, Yan
    He, Kaiming
    Kohli, Pushmeet
    Sun, Jian
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 3332 - 3339
  • [6] Probabilistic visualisation of high-dimensional binary data
    Tipping, ME
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11, 1999, 11 : 592 - 598
  • [7] High-dimensional affine codes
    Liu, Xiu-Feng
    Zhang, Ai-Li
    Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2005, 40 (02): : 179 - 183
  • [8] Model based clustering of high-dimensional binary data
    Tang, Yang
    Browne, Ryan P.
    Mc Nicholas, Paul D.
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2015, 87 : 84 - 101
  • [9] TopoMap: A 0-dimensional Homology Preserving Projection of High-Dimensional Data
    Doraiswamy, Harish
    Tierny, Julien
    Silva, Paulo J. S.
    Nonato, Luis Gustavo
    Silva, Claudio
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2021, 27 (02) : 561 - 571
  • [10] ON THE PERFORMANCE OF KERNEL ESTIMATORS FOR HIGH-DIMENSIONAL, SPARSE BINARY DATA
    GRUND, B
    HALL, P
    JOURNAL OF MULTIVARIATE ANALYSIS, 1993, 44 (02) : 321 - 344