mlsanityData to 14 Oct 2026

An Uncertainty Estimation Framework for Probabilistic Object Detection

arXiv 2106.15007 ↗First posted 28 Jun 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection. Quantifying uncertainty is critical in real-world robotic applications. Traditional detection models can be ambiguous even when they provide a high-probability output. Robot actions based on high-confidence, yet unreliable predictions, may result in serious repercussions. Our framework employs deep ensembles and Monte Carlo dropout for approximating predictive uncertainty, and it improves upon the uncertainty estimation quality of the baseline method. The proposed approach is evaluated on publicly available synthetic image datasets captured from sequences of video.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 28 Jun 2021.

Builds on

29 of 40 references.

References · 29

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2017Mask R-CNNcited by 7,277
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  9. 2015Fast R-CNNcited by 2,933
  10. 2018YOLOv3: An Incremental Improvementcited by 2,659
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  12. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
17 more
  1. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  2. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  5. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  6. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  7. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  8. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  9. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
  10. 2018Grid R-CNNcited by 85
  11. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  12. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  13. 2019Uncertainty Estimation in One-Stage Object Detectioncited by 36
  14. 2017Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolutioncited by 30
  15. 2014A Bayesian encourages dropoutcited by 6
  16. 2019The Probabilistic Object Detection Challengecited by 2
  17. 2019A Mask-RCNN Baseline for Probabilistic Object Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1; 2026: 2.

4 papers.

  1. 2026ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Controlcited by 5
  2. 2022Evaluating Uncertainty Calibration for Open-Set Recognitioncited by 1
  3. 2025ObjectTransforms for Uncertainty Quantification and Reduction in Vision-Based Perception for Autonomous Vehiclescited by 0
  4. 2026Leveraging Multi-Rater Annotations to Calibrate Object Detectors in Microscopy Imagingcited by 0