# MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection

arXiv: https://arxiv.org/abs/2010.01695 · HTML: https://mlsanity.com/paper/2010.01695/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications](https://mlsanity.com/paper/2111.01968/) (2021)
- [Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors](https://mlsanity.com/paper/2107.04517/) (2021)
- [MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification](https://mlsanity.com/paper/2405.19186/) (2024)
- [Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation](https://mlsanity.com/paper/2303.06920/) (2023)
- [Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving](https://mlsanity.com/paper/2107.04991/) (2021)
- [Post-hoc Models for Performance Estimation of Machine Learning Inference](https://mlsanity.com/paper/2110.02459/) (2021)
- [Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss](https://mlsanity.com/paper/2209.00364/) (2022)
- [LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds](https://mlsanity.com/paper/2306.07835/) (2023)
- [BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture](https://mlsanity.com/paper/2309.08036/) (2023)
- [Conformal Object Detection by Sequential Risk Control](https://mlsanity.com/paper/2505.24038/) (2025)
- [Machine vision-aware quality metrics for compressed image and video assessment](https://mlsanity.com/paper/2411.06776/) (2024)
- [Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -](https://mlsanity.com/paper/2504.12137/) (2025)
- [Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?](https://mlsanity.com/paper/2506.23751/) (2025)
- [Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning](https://mlsanity.com/paper/2205.14917/) (2022)
- [Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks](https://mlsanity.com/paper/2409.11373/) (2024)
- [From Label Error Detection to Correction: A Modular Framework and Benchmark for Object Detection Datasets](https://mlsanity.com/paper/2508.06556/) (2025)
- [From internal representations to model improvement through prediction errors](https://mlsanity.com/paper/2609.35449/) (2026)
- [Localisation-Aware Uncertainty for Pretrained Object Detection](https://mlsanity.com/paper/2610.01409/) (2026)

## Abstract (arXiv)

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 (mathitIoU≥0.5) and false positives (mathitIoU < 0.5) which we term meta classification, and we predict mathitIoU 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 mathitIoU. 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 R2 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.