Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation

TL;DR

This paper introduces a flexible, end-to-end deep learning framework that incorporates layer-wise cost estimation for improved cost-sensitive classification across various network structures.

Contribution

It proposes a novel, general framework that enables cost-sensitive learning in deep neural networks of any structure with layer-wise cost estimation and end-to-end training.

Findings

Outperforms existing cost-sensitive deep models on benchmark datasets.

Supports any network structure for cost-sensitive learning.

Enables end-to-end training with layer-wise cost estimation.

Abstract

While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with any structure to facilitate their learning of meaningful representations for cost-sensitive classification problems. Furthermore, the framework allows end-to-end training of deeper networks directly. The framework is designed by augmenting auxiliary neurons to the output of each hidden layer for layer-wise cost estimation, and including the total estimation loss within the optimization objective. Experimental results on public benchmark visual data sets with two cost information settings demonstrate that the proposed framework outperforms state-of-the-art cost-sensitive deep learning models.