Continual Evidential Deep Learning for Out-of-Distribution Detection

TL;DR

This paper introduces CEDL, a continual learning framework that combines evidential deep learning for improved out-of-distribution detection and incremental object classification.

Contribution

It integrates evidential deep learning into continual learning to enhance OOD detection and analyzes vacuity and dissonance for distinguishing in-distribution and OOD data.

Findings

CEDL achieves comparable classification accuracy to baselines.

CEDL significantly outperforms posthoc methods in OOD detection metrics.

The method effectively differentiates in-distribution old classes from OOD data.

Abstract

Uncertainty-based deep learning models have attracted a great deal of interest for their ability to provide accurate and reliable predictions. Evidential deep learning stands out achieving remarkable performance in detecting out-of-distribution (OOD) data with a single deterministic neural network. Motivated by this fact, in this paper we propose the integration of an evidential deep learning method into a continual learning framework in order to perform simultaneously incremental object classification and OOD detection. Moreover, we analyze the ability of vacuity and dissonance to differentiate between in-distribution data belonging to old classes and OOD data. The proposed method, called CEDL, is evaluated on CIFAR-100 considering two settings consisting of 5 and 10 tasks, respectively. From the obtained results, we could appreciate that the proposed method, in addition to provide comparable results in object classification with respect to the baseline, largely outperforms OOD detection compared to several posthoc methods on three evaluation metrics: AUROC, AUPR and FPR95.