Uncertainty in Real-Time Semantic Segmentation on Embedded Systems

TL;DR

This paper presents a method combining deep feature extraction with Bayesian regression to enable real-time, uncertainty-aware semantic segmentation on resource-constrained embedded systems.

Contribution

It introduces a novel approach that provides meaningful epistemic uncertainty estimates in real-time on embedded hardware, addressing a key challenge in the field.

Findings

The proposed method achieves real-time performance on embedded hardware.

It provides meaningful epistemic uncertainty estimates.

Predictive performance is maintained despite added uncertainty modeling.

Abstract

Application for semantic segmentation models in areas such as autonomous vehicles and human computer interaction require real-time predictive capabilities. The challenges of addressing real-time application is amplified by the need to operate on resource constrained hardware. Whilst development of real-time methods for these platforms has increased, these models are unable to sufficiently reason about uncertainty present when applied on embedded real-time systems. This paper addresses this by combining deep feature extraction from pre-trained models with Bayesian regression and moment propagation for uncertainty aware predictions. We demonstrate how the proposed method can yield meaningful epistemic uncertainty on embedded hardware in real-time whilst maintaining predictive performance.