Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data

TL;DR

This paper introduces a cost sensitive deep neural network that automatically learns robust features for imbalanced data, improving classification performance without altering data distribution.

Contribution

It presents a novel cost sensitive learning method that jointly optimizes class-dependent costs and neural network parameters for imbalanced datasets.

Findings

Significantly outperforms baseline algorithms on six image datasets.

Superior to data sampling and other cost sensitive methods.

Effective for both binary and multi-class problems.

Abstract

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an under-represented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this work, we propose a cost sensitive deep neural network which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multi-class problems without any modification. Moreover, as opposed to data level approaches, we do not alter the original data distribution which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification datasets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and cost sensitive classifiers demonstrate the superior performance of our proposed method.