# The Box Size Confidence Bias Harms Your Object Detector

arXiv: https://arxiv.org/abs/2112.01901 · HTML: https://mlsanity.com/paper/2112.01901/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 3 Dec 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Verified Uncertainty Calibration](https://mlsanity.com/paper/1909.10155/) (2019)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Multivariate Confidence Calibration for Object Detection](https://mlsanity.com/paper/2004.13546/) (2020)

## Built on by (most cited first, 5 of 5)

- [Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis](https://mlsanity.com/paper/2510.18229/) (2025)
- [Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration](https://mlsanity.com/paper/2309.03110/) (2023)
- [TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation](https://mlsanity.com/paper/2409.16678/) (2024)
- [Scale-Invariant Object Detection by Adaptive Convolution with Unified Global-Local Context](https://mlsanity.com/paper/2410.05274/) (2024)
- [From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models](https://mlsanity.com/paper/2607.26921/) (2026)

## Abstract (arXiv)

Countless applications depend on accurate predictions with reliable confidence estimates from modern object detectors. It is well known, however, that neural networks including object detectors produce miscalibrated confidence estimates. Recent work even suggests that detectors' confidence predictions are biased with respect to object size and position, but it is still unclear how this bias relates to the performance of the affected object detectors. We formally prove that the conditional confidence bias is harming the expected performance of object detectors and empirically validate these findings. Specifically, we demonstrate how to modify the histogram binning calibration to not only avoid performance impairment but also improve performance through conditional confidence calibration. We further find that the confidence bias is also present in detections generated on the training data of the detector, which we leverage to perform our de-biasing without using additional data. Moreover, Test Time Augmentation magnifies this bias, which results in even larger performance gains from our calibration method. Finally, we validate our findings on a diverse set of object detection architectures and show improvements of up to 0.6 mAP and 0.8 mAP50 without extra data or training.