paper-with-me

홈 › Papers

Optimal Correction Cost for Object Detection Evaluation

2022-03-28 · CVPR 2022 1 · Mayu Otani, Riku Togashi, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, Shin'ichi Satoh

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.

📄 PDF Abstract BibTeX arXiv:2203.14438

Code (1)

mayu-ot/oc-cost 공식 구현

Tasks

Objectobject-detectionObject DetectionRetrieval

Similar Papers 제목 키워드 기반

Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment

2025-09-16 · Avinaash Manoharan, Xiangyu Yin, Domenik Helm, Chih-Hong Cheng arxiv

Evaluating object detection models in deployment is challenging because ground-truth annotations are rarely available. We introduce the Cumulative Consensus Score (CCS), a label-free monitoring signal for continuous eval…

Data AugmentationObject Detection

Interpreting and Improving Optimal Control Problems with Directional Corrections

2025-04-01 · Trevor Barron, Xiaojing Zhang

Many robotics tasks, such as path planning or trajectory optimization, are formulated as optimal control problems (OCPs). The key to obtaining high performance lies in the design of the OCP's objective function. In pract…

Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation

2026-02-16 · Olivier Jeunen, Shashank Gupta arxiv

Off-policy evaluation (OPE) is essential for assessing ranking and recommendation systems without costly online interventions. Self-Normalised Inverse Propensity Scoring (SNIPS) is a standard tool for variance reduction …

Recommendation Systems

Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching

2026-03-11 · Takato Moriki, Hiromu Taketsugu, Norimichi Ukita arxiv

In Multi-Person Pose Estimation, many metrics place importance on ranking of pose detection confidence scores. Current metrics tend to disregard false-positive poses with low confidence, focusing primarily on a larger nu…

Multi-Person Pose Estimation

From Label Error Detection to Correction: A Modular Framework and Benchmark for Object Detection Datasets

2025-08-06 · Sarina Penquitt, Jonathan Klees, Rinor Cakaj, Daniel Kondermann 외 arxiv

Object detection has advanced rapidly in recent years, driven by increasingly large and diverse datasets. However, label errors often compromise the quality of these datasets and affect the outcomes of training and bench…

Label Error DetectionObject Detection