Confidence-Aware Learning for Deep Neural Networks

TL;DR

This paper introduces a simple, computationally efficient training method for deep neural networks that improves the quality of confidence estimates without modifying architectures, benefiting tasks like out-of-distribution detection and active learning.

Contribution

It proposes the Correctness Ranking Loss, a novel regularization technique that enhances confidence ranking in neural networks without additional computational costs or architecture changes.

Findings

Improves confidence estimation accuracy on benchmark datasets

Enhances out-of-distribution detection performance

Benefits active learning by providing reliable confidence scores

Abstract

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but most of them require either additional computational costs in training and/or inference phases or customized architectures to output confidence estimates separately. In this paper, we propose a method of training deep neural networks with a novel loss function, named Correctness Ranking Loss, which regularizes class probabilities explicitly to be better confidence estimates in terms of ordinal ranking according to confidence. The proposed method is easy to implement and can be applied to the existing architectures without any modification. Also, it has almost the same computational costs for training as conventional deep classifiers and outputs reliable predictions by a single inference. Extensive experimental results on classification benchmark datasets indicate that the proposed method helps networks to produce well-ranked confidence estimates. We also demonstrate that it is effective for the tasks closely related to confidence estimation, out-of-distribution detection and active learning.