An Uncertainty Estimation Framework for Probabilistic Object Detection
This work addresses uncertainty estimation for robotic applications, but it is incremental as it combines existing methods without introducing a fundamentally new approach.
The paper tackles the problem of unreliable high-confidence predictions in object detection by introducing a framework that combines deep ensembles and Monte Carlo dropout to estimate uncertainty, resulting in improved uncertainty estimation quality compared to a baseline method.
In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection. Quantifying uncertainty is critical in real-world robotic applications. Traditional detection models can be ambiguous even when they provide a high-probability output. Robot actions based on high-confidence, yet unreliable predictions, may result in serious repercussions. Our framework employs deep ensembles and Monte Carlo dropout for approximating predictive uncertainty, and it improves upon the uncertainty estimation quality of the baseline method. The proposed approach is evaluated on publicly available synthetic image datasets captured from sequences of video.