BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors
This work addresses uncertainty estimation for robotic systems using deep object detectors, representing an incremental improvement over existing methods.
The paper tackles the problem of uncertainty estimation in deep object detectors, which is crucial for robotic systems, by introducing BayesOD, a Bayesian approach that reformulates inference and non-maximum suppression to address information loss and multitask challenges, resulting in significant reductions of 9.77%-13.13% in Gaussian uncertainty error and 1.63%-5.23% in Categorical uncertainty error across four datasets.
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}}.