Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

TL;DR

This paper introduces a new training method for classifiers that improves their ability to detect out-of-distribution samples by jointly training classification and generative networks, leading to better confidence calibration.

Contribution

The authors propose a novel training approach that enhances confidence calibration for out-of-distribution detection by adding two loss terms and jointly training classifiers with generative models.

Findings

Improved OOD detection accuracy on image datasets

Enhanced confidence calibration in neural classifiers

Effective joint training of classification and generative models

Abstract

The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the state-of-art deep neural networks are known to be highly overconfident in their predictions, i.e., do not distinguish in- and out-of-distributions. Recently, to handle this issue, several threshold-based detectors have been proposed given pre-trained neural classifiers. However, the performance of prior works highly depends on how to train the classifiers since they only focus on improving inference procedures. In this paper, we develop a novel training method for classifiers so that such inference algorithms can work better. In particular, we suggest two additional terms added to the original loss (e.g., cross entropy). The first one forces samples from out-of-distribution less confident by the classifier and the second one is for (implicitly) generating most effective training samples for the first one. In essence, our method jointly trains both classification and generative neural networks for out-of-distribution. We demonstrate its effectiveness using deep convolutional neural networks on various popular image datasets.