Detection of False Positive and False Negative Samples in Semantic Segmentation

TL;DR

This paper reviews techniques for detecting false positive and false negative errors in semantic segmentation tasks using uncertainty quantification, emphasizing their importance for safety-critical applications.

Contribution

It introduces recent methods for self-monitoring of semantic segmentation models to identify error modes, with a focus on false positives and negatives, and discusses future research directions.

Findings

Reviewed uncertainty-based error detection techniques

Applied methods to semantic segmentation tasks

Provided outlook on future research

Abstract

In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.