# Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection

arXiv: https://arxiv.org/abs/1809.06006 · HTML: https://mlsanity.com/paper/1809.06006/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 30 of 51)

- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild](https://mlsanity.com/paper/2203.03800/) (2022)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Expanding Low-Density Latent Regions for Open-Set Object Detection](https://mlsanity.com/paper/2203.14911/) (2022)
- [A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/2104.10719/) (2021)
- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [Random Boxes Are Open-world Object Detectors](https://mlsanity.com/paper/2307.08249/) (2023)
- [Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects](https://mlsanity.com/paper/2303.13769/) (2023)
- [Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction](https://mlsanity.com/paper/2403.07263/) (2024)
- [Interpreting Object-level Foundation Models via Visual Precision Search](https://mlsanity.com/paper/2411.16198/) (2024)
- [Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration](https://mlsanity.com/paper/2307.00934/) (2023)
- [Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors](https://mlsanity.com/paper/2107.04517/) (2021)
- [Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection](https://mlsanity.com/paper/2302.07106/) (2023)
- [CertainNet: Sampling-free Uncertainty Estimation for Object Detection](https://mlsanity.com/paper/2110.01604/) (2021)
- [Bayesian Deep Learning for Affordance Segmentation in images](https://mlsanity.com/paper/2303.00871/) (2023)
- [Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving](https://mlsanity.com/paper/2107.04991/) (2021)
- [Generating Evidential BEV Maps in Continuous Driving Space](https://mlsanity.com/paper/2302.02928/) (2023)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Can OOD Object Detectors Learn from Foundation Models?](https://mlsanity.com/paper/2409.05162/) (2024)
- [Segmenting Known Objects and Unseen Unknowns without Prior Knowledge](https://mlsanity.com/paper/2209.05407/) (2022)
- [Towards Generalized Few-Shot Open-Set Object Detection](https://mlsanity.com/paper/2210.15996/) (2022)
- [PeSOTIF: a Challenging Visual Dataset for Perception SOTIF Problems in Long-tail Traffic Scenarios](https://mlsanity.com/paper/2211.03402/) (2022)
- [Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving](https://mlsanity.com/paper/2307.16121/) (2023)
- [SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving](https://mlsanity.com/paper/2211.04009/) (2022)
- [MarineDet: Towards Open-Marine Object Detection](https://mlsanity.com/paper/2310.01931/) (2023)
- [An Uncertainty Estimation Framework for Probabilistic Object Detection](https://mlsanity.com/paper/2106.15007/) (2021)
- [BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture](https://mlsanity.com/paper/2309.08036/) (2023)
- [Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection](https://mlsanity.com/paper/2404.17427/) (2024)

## Abstract (arXiv)

There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples, this is not the case for object detection, where detection sample bounding boxes must be accurately associated and merged. A weak merging strategy can significantly degrade the performance of the detector and yield an unreliable uncertainty measure. This paper provides the first in-depth investigation of the effect of different association and merging strategies. We compare different combinations of three spatial and two semantic affinity measures with four clustering methods for MC Dropout with a Single Shot Multi-Box Detector. Our results show that the correct choice of affinity-clustering combination can greatly improve the effectiveness of the classification and spatial uncertainty estimation and the resulting object detection performance. We base our evaluation on a new mix of datasets that emulate near open-set conditions (semantically similar unknown classes), distant open-set conditions (semantically dissimilar unknown classes) and the common closed-set conditions (only known classes).