新数据集COCO-FP揭示目标检测器在背景干扰下的误报问题。
From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors
- 构建新数据集COCO-FP，专测检测器对非标注背景物体的误检能力。
- YOLOv9-E在COCO-FP上AP50从72.8降至65.7，误报显著增加。
- 适合关注真实场景误报、部署前评估模型鲁棒性的研究者。
减少误报对提升目标检测器性能至关重要，这反映在平均精度（mAP）指标上。尽管当前检测器在COCO数据集上已取得显著进步并获得高mAP分数，但分析显示其在应对非目标视觉干扰——即未标注类别中的背景物体——导致的误报方面进展有限。该问题在火灾与烟雾检测等真实应用场景中尤为关键，因需最大限度降低误报。为此，本文提出COCO-FP，一个基于ImageNet-1K构建的新评估数据集，扩展原版COCO验证集，专门评估检测器在减少背景误报上的表现。对标准与先进检测器的评估表明，在封闭集和开放集场景下均存在大量误报。例如，YOLOv9-E在从COCO切换到COCO-FP时，AP50从72.8下降至65.7。数据集已开源：https://github.com/COCO-FP/COCO-FP。
原文摘要 · Abstract (English)
Reducing false positives is essential for enhancing object detector performance, as reflected in the mean Average Precision (mAP) metric. Although object detectors have achieved notable improvements and high mAP scores on the COCO dataset, analysis reveals limited progress in addressing false positives caused by non-target visual clutter-background objects not included in the annotated categories. This issue is particularly critical in real-world applications, such as fire and smoke detection, where minimizing false alarms is crucial. In this study, we introduce COCO-FP, a new evaluation dataset derived from the ImageNet-1K dataset, designed to address this issue. By extending the original COCO validation dataset, COCO-FP specifically assesses object detectors' performance in mitigating background false positives. Our evaluation of both standard and advanced object detectors shows a significant number of false positives in both closed-set and open-set scenarios. For example, the AP50 metric for YOLOv9-E decreases from 72.8 to 65.7 when shifting from COCO to COCO-FP. The dataset is available at https://github.com/COCO-FP/COCO-FP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。