Uncertainty in Real-Time Semantic Segmentation on Embedded Systems
This addresses the need for uncertainty-aware predictions in real-time applications like autonomous vehicles on resource-constrained hardware, representing an incremental improvement over existing methods.
The paper tackles the problem of enabling real-time semantic segmentation models on embedded systems to reason about uncertainty, combining deep feature extraction with Bayesian regression and moment propagation to achieve meaningful epistemic uncertainty without compromising predictive performance.
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.