Class Uncertainty: A Measure to Mitigate Class Imbalance - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Class Uncertainty: A Measure to Mitigate Class Imbalance

Résumé

Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long-tailed distribution, a situation that is likely to yield suboptimal performance for under-represented classes. This class imbalance problem is conventionally addressed by approaches relying on the class-wise cardinality of training examples, such as data resampling. In this paper, we demonstrate that considering solely the cardinality of classes does not cover all issues causing class imbalance. To measure class imbalance, we propose CLASS UNCERTAINTY as the average predictive uncertainty of the training examples, and we show that this novel measure captures the differences across classes better than cardinality. We also curate SVCI-20 as a novel dataset in which the classes have equal number of training examples but they differ in terms of their hardness; thereby causing a type of class imbalance which cannot be addressed by the approaches relying on cardinality. We incorporate our CLASS UNCERTAINTY measure into a diverse set of ten class imbalance mitigation methods to demonstrate its effectiveness on long-tailed datasets as well as on our SVCI-20. Code and datasets will be made available.
Fichier principal
Vignette du fichier
2311.14090.pdf (580.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04317284 , version 1 (01-12-2023)

Identifiants

Citer

Zeynep Sonat Baltaci, Kemal Oksuz, Selim Kuzucu, Kivanc Tezoren, Berkin Kerim Konar, et al.. Class Uncertainty: A Measure to Mitigate Class Imbalance. 2023. ⟨hal-04317284⟩
39 Consultations
12 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More