Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep ordinal regression with label diversity

Berg, Axel LU orcid ; Oskarsson, Magnus LU orcid and O'Connor, Mark (2021) 2020 25th International Conference on Pattern Recognition In International Conference on Pattern Recognition p.2740-2747
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2020 25th International Conference on Pattern Recognition (ICPR)
series title
International Conference on Pattern Recognition
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2020 25th International Conference on Pattern Recognition
conference location
Milan, Italy
conference dates
2021-01-10 - 2021-01-15
external identifiers
  • scopus:85110495846
ISSN
1051-4651
ISBN
978-1-7281-8808-9
DOI
10.1109/ICPR48806.2021.9412608
project
Deep Learning for Simultaneous Localization and Mapping
language
English
LU publication?
yes
id
2f6e765c-7016-4a5a-98ab-c6c95ae28cf0
alternative location
https://arxiv.org/abs/2006.15864
date added to LUP
2021-05-11 11:45:17
date last changed
2024-11-18 03:25:54
@inproceedings{2f6e765c-7016-4a5a-98ab-c6c95ae28cf0,
  abstract     = {{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.}},
  author       = {{Berg, Axel and Oskarsson, Magnus and O'Connor, Mark}},
  booktitle    = {{2020 25th International Conference on Pattern Recognition (ICPR)}},
  isbn         = {{978-1-7281-8808-9}},
  issn         = {{1051-4651}},
  language     = {{eng}},
  pages        = {{2740--2747}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{International Conference on Pattern Recognition}},
  title        = {{Deep ordinal regression with label diversity}},
  url          = {{http://dx.doi.org/10.1109/ICPR48806.2021.9412608}},
  doi          = {{10.1109/ICPR48806.2021.9412608}},
  year         = {{2021}},
}