Real-world data often exhibits class-imbalanced distributions, where a few classes (aka
majority classes) occupy most instances and lots of classes (aka minority classes) have few …

Data in vision domain often exhibit highly-skewed class distribution, ie, most data belong to
a few majority classes, while the minority classes only contain a scarce amount of instances …

In this paper, we propose a balancing training method to address problems in imbalanced
data learning. To this end, we derive a new loss used in the balancing training phase that …

In most real-world scenarios, labeled training datasets are highly class-imbalanced, where
deep neural networks suffer from generalizing to a balanced testing criterion. In this paper …

Real-world object classes appear in imbalanced ratios. This poses a significant challenge
for classifiers which get biased towards frequent classes. We hypothesize that improving the …

Class-imbalance is one of the major challenges in real world datasets where a few classes
(called majority classes) constitute much more data samples than the rest (called minority …

A challenging problem in object recognition is to train a robust classifier with small and
imbalanced data set. In such cases, the learned classifier tends to overfit the training data …

Imbalanced class distribution is an inherent problem in many real-world classification tasks
where the minority class is the class of interest. Many conventional statistical and machine …

The problem of class imbalance has always been considered as a significant challenge to
traditional machine learning and the emerging deep learning research communities. A …

Although the class-imbalance classification problem has caught a huge amount of attention,
hyperparameter optimisation has not been studied in detail in this field. Both classification …