Learning Balanced Trees for Large Scale Image Classification

被引:2
|
作者
Tien-Dung Mai [1 ]
Thanh Duc Ngo [1 ]
Duy-Dinh Le [1 ,2 ]
Duc Anh Duong [1 ]
Hoang, Kiem [1 ]
Satoh, Shin'ichi [2 ]
机构
[1] VNU HCM, Univ Informat Technol, Ho Chi Minh City, Vietnam
[2] Res Org Informat & Syst, Natl Inst Informat, Chiyoda Ku, Tokyo 1018430, Japan
来源
IMAGE ANALYSIS AND PROCESSING - ICIAP 2015, PT II | 2015年 / 9280卷
关键词
D O I
10.1007/978-3-319-23234-8_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The label tree is one of the popular approaches for the problem of large scale multi-class image classification in which the number of class labels is large, for example, several tens of thousands of labels. In learning stage, class labels are organized into a hierarchical tree, in which each node is associated with a subset of class labels and a classifier that determines which branch to follow; and each leaf node is associated with a single class label. In testing stage, the fact that a test example travels from the root of the tree to a leaf node reduces the test time significantly compared to the approach of using multiple binary one-versus-all classifiers. The balance of the learned tree structure is the key essential of the label tree approach. Previous methods for learning the tree structure use clustering techniques such as k-means or spectral clustering to group confused labels into clusters associated with the nodes. However, the output tree might not be balanced. We propose a method for learning effective and balanced tree structure by jointly optimizing the balance constraint and the confusion constraint. The experimental results on the datasets such as Caltech-256, SUN-397, and ImageNet-1K show that the classification accuracy of the proposed approach outperforms that of other state of the art methods.
引用
收藏
页码:3 / 13
页数:11
相关论文
共 50 条
  • [41] Classification of large-scale image database of various skin diseases using deep learning
    Tanaka, Masaya
    Saito, Atsushi
    Shido, Kosuke
    Fujisawa, Yasuhiro
    Yamasaki, Kenshi
    Fujimoto, Manabu
    Murao, Kohei
    Ninomiya, Youichirou
    Satoh, Shin'ichi
    Shimizu, Akinobu
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2021, 16 (11) : 1875 - 1887
  • [42] Discrete semi-supervised learning for multi-label image classification and large-scale image retrieval
    He, Lang
    Xie, Liang
    Shu, Haohao
    Hu, Shengyuan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (17) : 24519 - 24537
  • [43] Discrete semi-supervised learning for multi-label image classification and large-scale image retrieval
    Lang He
    Liang Xie
    Haohao Shu
    Shengyuan Hu
    Multimedia Tools and Applications, 2019, 78 : 24519 - 24537
  • [44] Learning Balanced Tree Indexes for Large-Scale Vector Retrieval
    Li, Wuchao
    Feng, Chao
    Lian, Defu
    Xie, Yuxin
    Liu, Haifeng
    Ge, Yong
    Chen, Enhong
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 1353 - 1362
  • [45] Machine learning approaches for large scale classification of produce
    Otkrist Gupta
    Anshuman J. Das
    Joshua Hellerstein
    Ramesh Raskar
    Scientific Reports, 8
  • [46] Machine learning approaches for large scale classification of produce
    Gupta, Otkrist
    Das, Anshuman J.
    Hellerstein, Joshua
    Raskar, Ramesh
    SCIENTIFIC REPORTS, 2018, 8
  • [47] Learning Taxonomy Adaptation in Large-scale Classification
    Babbar, Rohit
    Partalas, Ioannis
    Gaussier, Eric
    Amini, Massih-Reza
    Amblard, Cecile
    JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17
  • [48] LARGE-SCALE NONLINEAR FACIAL IMAGE CLASSIFICATION BASED ON APPROXIMATE KERNEL EXTREME LEARNING MACHIINE
    Iosifidis, Alexandros
    Tefas, Anastasios
    Pitas, Ioannis
    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 2449 - 2453
  • [49] Fashion style classification by weakly supervised learning using large-scale clothing image database
    Minoguchi M.
    Watabe K.
    Yamada R.
    Kataoka H.
    Nakamura A.
    Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, 2021, 87 (01): : 92 - 98
  • [50] Large-Scale Multi-Class Image-Based Cell Classification With Deep Learning
    Meng, Nan
    Lam, Edmund Y.
    Tsia, Kevin K.
    So, Hayden Kwok-Hay
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (05) : 2091 - 2098