DeepAI AI Chat
Log In Sign Up

A systematic study of the class imbalance problem in convolutional neural networks

by   Mateusz Buda, et al.

In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that totally eliminates the imbalance, whereas undersampling can perform better when the imbalance is only removed to some extent; (iv) as opposed to some classical machine learning models, oversampling does not necessarily cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest.


page 1

page 2

page 3

page 4


An Empirical Study on the Joint Impact of Feature Selection and Data Resampling on Imbalance Classification

Real-world datasets often present different degrees of imbalanced (i.e.,...

Imbalanced Malware Images Classification: a CNN based Approach

Deep convolutional neural networks (CNNs) can be applied to malware bina...

On the combined effect of class imbalance and concept complexity in deep learning

Structural concept complexity, class overlap, and data scarcity are some...

Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networks

Imbalanced Data (ID) is a problem that deters Machine Learning (ML) mode...

Bad practices in evaluation methodology relevant to class-imbalanced problems

For research to go in the right direction, it is essential to be able to...