Deep Ordinal Regression with Label Diversity

被引:20
|
作者
Berg, Axel [1 ,2 ]
Oskarsson, Magnus [2 ]
O'Connor, Mark [1 ]
机构
[1] Arm Res, Cambridge, England
[2] Lund Univ, Ctr Math Sci, Lund, Sweden
关键词
HEAD POSE ESTIMATION;
D O I
10.1109/ICPR48806.2021.9412608
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach. However, it is not clear how the set of discrete classes should be chosen and how it affects the overall solution. In this work, we propose that using several discrete data representations simultaneously can improve neural network learning compared to a single representation. Our approach is end-to-end differentiable and can be added as a simple extension to conventional learning methods, such as deep neural networks. We test our method on three challenging tasks and show that our method reduces the prediction error compared to a baseline RvC approach while maintaining a similar model complexity.
引用
收藏
页码:2740 / 2747
页数:8
相关论文
共 50 条
  • [1] A novel transformer ordinal regression network with label diversity for wind power ramp events forecasting
    Hu, Jianming
    Zhang, Liping
    Tang, Jingwei
    Liu, Zhi
    [J]. ENERGY, 2023, 280
  • [2] Deep and interpretable regression models for ordinal outcomes
    Kook, Lucas
    Herzog, Lisa
    Hothorn, Torsten
    Durr, Oliver
    Sick, Beate
    [J]. PATTERN RECOGNITION, 2022, 122
  • [3] A Constrained Deep Neural Network for Ordinal Regression
    Liu, Yanzhu
    Kong, Adams Wai Kin
    Goh, Chi Keong
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 831 - 839
  • [4] Deep Ordinal Regression for Pledge Specificity Prediction
    Subramanian, Shivashankar
    Cohn, Trevor
    Baldwin, Timothy
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 1729 - 1740
  • [5] Deep Ordinal Regression Network for Monocular Depth Estimation
    Fu, Huan
    Gong, Mingming
    Wang, Chaohui
    Batmanghelich, Kayhan
    Tao, Dacheng
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2002 - 2011
  • [6] Probabilistic Deep Ordinal Regression Based on Gaussian Processes
    Liu, Yanzhu
    Wang, Fan
    Kong, Adams Wai Kin
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5300 - 5308
  • [7] Distributed robust support vector ordinal regression under label noise
    Liu, Huan
    Tu, Jiankai
    Gao, Anqi
    Li, Chunguang
    [J]. NEUROCOMPUTING, 2024, 598
  • [8] Image Visual Complexity Evaluation Based on Deep Ordinal Regression
    Guo, Xiaoying
    Wang, Lu
    Yan, Tao
    Wei, Yanfeng
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XI, 2024, 14435 : 199 - 210
  • [9] Unimodal regularisation based on beta distribution for deep ordinal regression
    Manuel Vargas, Victor
    Antonio Gutierrez, Pedro
    Hervas-Martinez, Cesar
    [J]. PATTERN RECOGNITION, 2022, 122
  • [10] Deep Ordinal Regression Based on Data Relationship for Small Datasets
    Liu, Yanzhu
    Kong, Adams Wai Kin
    Goh, Chi Keong
    [J]. PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2372 - 2378