Title
A step towards understanding why classification helps regression
Author
Pintea, S. (TU Delft Pattern Recognition and Bioinformatics; Leiden University Medical Center) 
Lin, Y. (TU Delft Intelligent Vehicles)
Dijkstra, Jouke (Leiden University Medical Center)
van Gemert, J.C. (TU Delft Pattern Recognition and Bioinformatics)
Contributor
Ceballos, Cristina (editor)
Date
2023
Abstract
A number of computer vision deep regression approaches report improved results when adding a classification loss to the regression loss. Here, we explore why this is useful in practice and when it is beneficial. To do so, we start from precisely controlled dataset variations and data samplings and find that the effect of adding a classification loss is the most pronounced for regression with imbalanced data. We explain these empirical findings by formalizing the relation between the balanced and imbalanced regression losses. Finally, we show that our findings hold on two real imbalanced image datasets for depth estimation (NYUD2-DIR), and age estimation (IMDB-WIKI-DIR), and on the problem of imbalanced video progress prediction (Breakfast). Our main takeaway is: for a regression task, if the data sampling is imbalanced, then add a classification loss.
To reference this document use:
http://resolver.tudelft.nl/uuid:380cfc42-b50d-4f5c-a5ad-76f31978096f
DOI
https://doi.org/10.1109/ICCV51070.2023.01828
Publisher
IEEE, Piscataway
Embargo date
2024-07-15
ISBN
979-8-3503-0719-1
Source
Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Event
2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023-10-01 → 2023-10-06, Paris, France
Series
Proceedings of the IEEE International Conference on Computer Vision, 1550-5499
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2023 S. Pintea, Y. Lin, Jouke Dijkstra, J.C. van Gemert