# Optimal Correction Cost for Object Detection Evaluation

arXiv: https://arxiv.org/abs/2203.14438 · HTML: https://mlsanity.com/paper/2203.14438/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 13 of 13)

- [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)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details](https://mlsanity.com/paper/2102.01066/) (2021)
- [Probabilistic Object Detection: Definition and Evaluation](https://mlsanity.com/paper/1811.10800/) (2018)
- [Localization Recall Precision (LRP): A New Performance Metric for Object Detection](https://mlsanity.com/paper/1807.01696/) (2018)
- [LayoutGMN: Neural Graph Matching for Structural Layout Similarity](https://mlsanity.com/paper/2012.06547/) (2020)

## Built on by (most cited first, 11 of 11)

- [S2O: Static to Openable Enhancement for Articulated 3D Objects](https://mlsanity.com/paper/2409.18896/) (2024)
- [Unbalanced Optimal Transport: A Unified Framework for Object Detection](https://mlsanity.com/paper/2307.02402/) (2023)
- [On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines](https://mlsanity.com/paper/2405.20459/) (2024)
- [LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generation](https://mlsanity.com/paper/2407.12356/) (2024)
- [LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generation](https://mlsanity.com/paper/2506.02697/) (2025)
- [Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection](https://mlsanity.com/paper/2508.18729/) (2025)
- [Fractional Correspondence Framework in Detection Transformer](https://mlsanity.com/paper/2503.04107/) (2025)
- [FuzzRisk: Online Collision Risk Estimation for Autonomous Vehicles based on Depth-Aware Object Detection via Fuzzy Inference](https://mlsanity.com/paper/2411.08060/) (2024)
- [Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment](https://mlsanity.com/paper/2509.12871/) (2025)
- [Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching](https://mlsanity.com/paper/2603.10398/) (2026)
- [Quantifying Annotation Agreement in Object Detection with Optimal Transport](https://mlsanity.com/paper/2610.19912/) (2026)

## Abstract (arXiv)

Mean Average Precision (mAP) is the primary evaluation measure for object detection. Although object detection has a broad range of applications, mAP evaluates detectors in terms of the performance of ranked instance retrieval. Such the assumption for the evaluation task does not suit some downstream tasks. To alleviate the gap between downstream tasks and the evaluation scenario, we propose Optimal Correction Cost (OC-cost), which assesses detection accuracy at image level. OC-cost computes the cost of correcting detections to ground truths as a measure of accuracy. The cost is obtained by solving an optimal transportation problem between the detections and the ground truths. Unlike mAP, OC-cost is designed to penalize false positive and false negative detections properly, and every image in a dataset is treated equally. Our experimental result validates that OC-cost has better agreement with human preference than a ranking-based measure, i.e., mAP for a single image. We also show that detectors' rankings by OC-cost are more consistent on different data splits than mAP. Our goal is not to replace mAP with OC-cost but provide an additional tool to evaluate detectors from another aspect. To help future researchers and developers choose a target measure, we provide a series of experiments to clarify how mAP and OC-cost differ.