Papers βΊ MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection
MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection
Marius Schubert, Karsten Kahl, Matthias Rottmann
In object detection with deep neural networks, the box-wise objectness score tends to be overconfident, sometimes even indicating high confidence in presence of inaccurate predictions. Hence, the reliability of the prediction and therefore reliable uncertainties are of highest interest. In this work, we present a post processing method that for any given neural network provides predictive uncertainty estimates and quality estimates. These estimates are learned by a post processing model that receives as input a hand-crafted set of transparent metrics in form of a structured dataset. Therefrom, we learn two tasks for predicted bounding boxes. We discriminate between true positives (πΌππβ₯0.5) and false positives (πΌππ < 0.5) which we term meta classification, and we predict πΌππ values directly which we term meta regression. The probabilities of the meta classification model aim at learning the probabilities of success and failure and therefore provide a modelled predictive uncertainty estimate. On the other hand, meta regression gives rise to a quality estimate. In numerical experiments, we use the publicly available YOLOv3 network and the Faster-RCNN network and evaluate meta classification and regression performance on the Kitti, Pascal VOC and COCO datasets. We demonstrate that our metrics are indeed well correlated with the πΌππ. For meta classification we obtain classification accuracies of up to 98.92% and AUROCs of up to 99.93%. For meta regression we obtain an RΒ² value of up to 91.78%. These results yield significant improvements compared to other network's objectness score and other baseline approaches. Therefore, we obtain more reliable uncertainty and quality estimates which is particularly interesting in the absence of ground truth.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change Β· a person checks every report against the paper or source before anything changes; decisions are listed on /corrections