Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

TL;DR

This paper introduces a novel evidential modeling approach for visual recognition that explicitly quantifies confusion and ignorance uncertainties, enabling dynamic predictions and rejection of out-of-distribution inputs.

Contribution

It proposes modeling confusion and ignorance separately using Subjective Logic, allowing flexible recognition with uncertainty quantification and out-of-distribution rejection.

Findings

Effective quantification of inter-class confusion and out-of-distribution ignorance.

Improved recognition accuracy with uncertainty-aware predictions.

Successful application to synthetic, visual, and open-set detection tasks.

Abstract

In real-world scenarios, typical visual recognition systems could fail under two major causes, i.e., the misclassification between known classes and the excusable misbehavior on unknown-class images. To tackle these deficiencies, flexible visual recognition should dynamically predict multiple classes when they are unconfident between choices and reject making predictions when the input is entirely out of the training distribution. Two challenges emerge along with this novel task. First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples. Second, both confusion and ignorance should be comparable between samples to enable effective decision-making. In this paper, we propose to model these two sources of uncertainty explicitly with the theory of Subjective Logic. Regarding recognition as an evidence-collecting process, confusion is then defined as conflicting evidence, while ignorance is the absence of evidence. By predicting Dirichlet concentration parameters for singletons, comprehensive subjective opinions, including confusion and ignorance, could be achieved via further evidence combinations. Through a series of experiments on synthetic data analysis, visual recognition, and open-set detection, we demonstrate the effectiveness of our methods in quantifying two sources of uncertainties and dealing with flexible recognition.