# BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors

## TL;DR

BayesOD introduces a Bayesian framework for deep object detectors that improves uncertainty estimation by addressing information loss during NMS and the multitask detection process, leading to more reliable confidence measures.

## Contribution

It reformulates object detection inference and NMS from a Bayesian perspective, enhancing uncertainty estimation in deep neural network-based detectors.

## Key findings

- Significant reduction in Gaussian uncertainty error (9.77%-13.13%)
- Significant reduction in Categorical uncertainty error (1.63%-5.23%)
- Better correlation between uncertainty estimates and detection accuracy

## Abstract

When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions. Methods for uncertainty estimation in the output of deep object detectors (DNNs) have been proposed in recent works, but have had limited success due to 1) information loss at the detectors non-maximum suppression (NMS) stage, and 2) failure to take into account the multitask, many-to-one nature of anchor-based object detection. To that end, we introduce BayesOD, an uncertainty estimation approach that reformulates the standard object detector inference and Non-Maximum suppression components from a Bayesian perspective. Experiments performed on four common object detection datasets show that BayesOD provides uncertainty estimates that are better correlated with the accuracy of detections, manifesting as a significant reduction of 9.77\%-13.13\% on the minimum Gaussian uncertainty error metric and a reduction of 1.63\%-5.23\% on the minimum Categorical uncertainty error metric. Code will be released at {\url{https://github.com/asharakeh/bayes-od-rc}}.