A step towards understanding why classification helps regression
IEEE/CVF International Conference on Computer Vision (ICCV), pp. 19915–19924
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.
Authors 4
-
Leiden University Medical Center · Delft University of Technology
Affiliation as printed
Delft University of Technology,Computer Vision Lab
Computer Vision Lab, Delft University of Technology
Division of Image Processing (LKEB), Leiden University Medical Center
-
Delft University of Technology
Affiliation as printed
Delft University of Technology,Intelligent Vehicles Group
Intelligent Vehicles Group, Delft University of Technology
-
Leiden University Medical Center
Affiliation as printed
Leiden University Medical Center,Division of Image Processing (LKEB)
Division of Image Processing (LKEB), Leiden University Medical Center
-
Delft University of Technology
Affiliation as printed
Delft University of Technology,Computer Vision Lab
Computer Vision Lab, Delft University of Technology
Cited by 10 stored of 10
10 results
No patents citing this paper on Lens.org (checked 2026-10-11).