# Towards Improving Calibration in Object Detection Under Domain Shift

arXiv: https://arxiv.org/abs/2209.07601 · HTML: https://mlsanity.com/paper/2209.07601/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 15 Sep 2022.

## Builds on (most cited first, 30 of 37)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Improving model calibration with accuracy versus uncertainty optimization](https://mlsanity.com/paper/2012.07923/) (2020)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [Multivariate Confidence Calibration for Object Detection](https://mlsanity.com/paper/2004.13546/) (2020)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Post-hoc Uncertainty Calibration for Domain Drift Scenarios](https://mlsanity.com/paper/2012.10988/) (2020)
- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://mlsanity.com/paper/2203.13834/) (2022)
- [Analyzing the Role of Model Uncertainty for Electronic Health Records](https://mlsanity.com/paper/1906.03842/) (2019)
- [Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification](https://mlsanity.com/paper/2009.04057/) (2020)

## Built on by (most cited first, 26 of 26)

- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [On Calibrating Semantic Segmentation Models: Analyses and An Algorithm](https://mlsanity.com/paper/2212.12053/) (2022)
- [Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration](https://mlsanity.com/paper/2307.00934/) (2023)
- [MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection](https://mlsanity.com/paper/2309.14976/) (2023)
- [O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models](https://mlsanity.com/paper/2503.12096/) (2025)
- [Cal-DETR: Calibrated Detection Transformer](https://mlsanity.com/paper/2311.03570/) (2023)
- [Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding](https://mlsanity.com/paper/2403.17010/) (2024)
- [On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines](https://mlsanity.com/paper/2405.20459/) (2024)
- [Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping](https://mlsanity.com/paper/2306.04985/) (2023)
- [Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection](https://mlsanity.com/paper/2312.06645/) (2023)
- [ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning](https://mlsanity.com/paper/2409.18026/) (2024)
- [AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images](https://mlsanity.com/paper/2312.06106/) (2023)
- [A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models](https://mlsanity.com/paper/2510.26441/) (2025)
- [OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning](https://mlsanity.com/paper/2407.02386/) (2024)
- [Uncertainty Quantification in Detection Transformers: Object-Level Calibration and Image-Level Reliability](https://mlsanity.com/paper/2412.01782/) (2024)
- [A Theoretical and Practical Framework for Evaluating Uncertainty Calibration in Object Detection](https://mlsanity.com/paper/2309.00464/) (2023)
- [CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence](https://mlsanity.com/paper/2310.06380/) (2023)
- [Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting](https://mlsanity.com/paper/2402.03292/) (2024)
- [TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation](https://mlsanity.com/paper/2409.16678/) (2024)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift](https://mlsanity.com/paper/2605.05328/) (2026)
- [Calibrating Probabilistic Object Detectors with Annotator Disagreement](https://mlsanity.com/paper/2605.24722/) (2026)
- [Rethinking Detection Calibration: A Coordinate and Direction Perspective](https://mlsanity.com/paper/2607.29040/) (2026)
- [Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition](https://mlsanity.com/paper/2608.17917/) (2026)
- [Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary](https://mlsanity.com/paper/2609.36426/) (2026)

## Abstract (arXiv)

With deep neural network based solution more readily being incorporated in real-world applications, it has been pressing requirement that predictions by such models, especially in safety-critical environments, be highly accurate and well-calibrated. Although some techniques addressing DNN calibration have been proposed, they are only limited to visual classification applications and in-domain predictions. Unfortunately, very little to no attention is paid towards addressing calibration of DNN-based visual object detectors, that occupy similar space and importance in many decision making systems as their visual classification counterparts. In this work, we study the calibration of DNN-based object detection models, particularly under domain shift. To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD). It can be used with various application-specific loss functions as an auxiliary loss function to improve detection calibration. Second, we devise a new implicit technique for improving calibration in self-training based domain adaptive detectors, featuring a new uncertainty quantification mechanism for object detection. We demonstrate TCD is capable of enhancing calibration with notable margins (1) across different DNN-based object detection paradigms both in in-domain and out-of-domain predictions, and (2) in different domain-adaptive detectors across challenging adaptation scenarios. Finally, we empirically show that our implicit calibration technique can be used in tandem with TCD during adaptation to further boost calibration in diverse domain shift scenarios.