Deep Over-sampling Framework for Classifying Imbalanced Data

TL;DR

This paper introduces Deep Over-sampling (DOS), a novel framework that enhances deep learning models' ability to handle imbalanced data by leveraging supervised representation learning and synthetic embedding targets in the deep feature space.

Contribution

The paper proposes a new deep over-sampling framework that extends synthetic over-sampling to deep feature spaces, improving class imbalance handling and CNN performance.

Findings

DOS outperforms existing methods on public benchmarks.

It improves CNN performance in both imbalanced and balanced settings.

The framework reduces in-class variance in embeddings.

Abstract

Class imbalance is a challenging issue in practical classification problems for deep learning models as well as traditional models. Traditionally successful countermeasures such as synthetic over-sampling have had limited success with complex, structured data handled by deep learning models. In this paper, we propose Deep Over-sampling (DOS), a framework for extending the synthetic over-sampling method to exploit the deep feature space acquired by a convolutional neural network (CNN). Its key feature is an explicit, supervised representation learning, for which the training data presents each raw input sample with a synthetic embedding target in the deep feature space, which is sampled from the linear subspace of in-class neighbors. We implement an iterative process of training the CNN and updating the targets, which induces smaller in-class variance among the embeddings, to increase the discriminative power of the deep representation. We present an empirical study using public benchmarks, which shows that the DOS framework not only counteracts class imbalance better than the existing method, but also improves the performance of the CNN in the standard, balanced settings.