mlsanityData to 7 Oct 2026

Multivariate Confidence Calibration for Object Detection

arXiv 2004.13546 ↗First posted 28 Apr 2020cs.CV cs.LG stat.MLcited by 98

Not on the map. Why?

Abstract (arXiv)

Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification, the field of object detection has not been addressed yet. Therefore, we present a novel framework to measure and calibrate biased (or miscalibrated) confidence estimates of object detection methods. The main difference to related work in the field of classifier calibration is that we also use additional information of the regression output of an object detector for calibration. Our approach allows, for the first time, to obtain calibrated confidence estimates with respect to image location and box scale. In addition, we propose a new measure to evaluate miscalibration of object detectors. Finally, we show that our developed methods outperform state-of-the-art calibration models for the task of object detection and provides reliable confidence estimates across different locations and scales.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 17; 2023: 25; 2024: 14; 2025: 13; 2026: 16.

98 papers.

Sort:

By area:

  1. 2021Evaluating Large-Vocabulary Object Detectors: The Devil is in the Detailscited by 57
  2. 2022Annotation Error Detection: Analyzing the Past and Present for a More Coherent Futurecited by 45
  3. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  4. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  5. 2022TeST: Test-time Self-Training under Distribution Shiftcited by 29
  6. 2024Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignmentcited by 29
  7. 2022Towards Improving Calibration in Object Detection Under Domain Shiftcited by 26
  8. 2021Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detectioncited by 24
  9. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
  10. 2023Task-Aware Information Routing from Common Representation Space in Lifelong Learningcited by 22
  11. 2023Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibrationcited by 19
  12. 2022ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the UScited by 17
38 more
  1. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detectioncited by 17
  2. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  3. 2023Multiclass Confidence and Localization Calibration for Object Detectioncited by 16
  4. 2022Consistency is the key to further mitigating catastrophic forgetting in continual learningcited by 14
  5. 2022Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approachcited by 13
  6. 2022Are we certain it's anomalous?cited by 13
  7. 2021Connecting Low-Loss Subspace for Personalized Federated Learningcited by 12
  8. 2022A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Surveycited by 12
  9. 2023Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detectioncited by 12
  10. 2023Cal-DETR: Calibrated Detection Transformercited by 11
  11. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  12. 2024On Calibration of Object Detectors: Pitfalls, Evaluation and Baselinescited by 11
  13. 2024Confidence Calibration of Classifiers with Many Classescited by 11
  14. 2023Calibrated Teacher for Sparsely Annotated Object Detectioncited by 10
  15. 2023Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detectioncited by 9
  16. 2021From Black-box to White-box: Examining Confidence Calibration under different Conditionscited by 8
  17. 2022A Comprehensive Study of Vision Transformers on Dense Prediction Taskscited by 8
  18. 2022Parametric and Multivariate Uncertainty Calibration for Regression and Object Detectioncited by 8
  19. 2023Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networkscited by 7
  20. 2023On the Limitations of Temperature Scaling for Distributions with Overlapscited by 7
  21. 2023Quantifying and mitigating the impact of label errors on model disparity metricscited by 7
  22. 2021False Negative Reduction in Video Instance Segmentation using Uncertainty Estimatescited by 6
  23. 2023Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networkscited by 6
  24. 2023Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learningcited by 6
  25. 2024ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learningcited by 6
  26. 2024DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domainscited by 6
  27. 2025Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detectioncited by 6
  28. 2021Bayesian Confidence Calibration for Epistemic Uncertainty Modellingcited by 5
  29. 2021The Box Size Confidence Bias Harms Your Object Detectorcited by 5
  30. 2022Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Componentscited by 5
  31. 2022Confidence Calibration for Object Detection and Segmentationcited by 5
  32. 2024Fractal Calibration for long-tailed object detectioncited by 5
  33. 2025Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequenciescited by 5
  34. 2022Active Learning and Novel Model Calibration Measurements for Automated Visual Inspection in Manufacturingcited by 4
  35. 2023A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layercited by 4
  36. 2023The Limits of Fair Medical Imaging AI In The Wildcited by 4
  37. 2024IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learningcited by 4
  38. 2021Post-hoc Models for Performance Estimation of Machine Learning Inferencecited by 3

50 most cited of 98 All 98 (JSON)