arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.07907cs.CV
收藏

从COCO到COCO-FP:深入探究COCO检测器的背景假阳性问题

From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors

Intellindust(英泰利工业);Guilin University Of Electronic Technology(桂林电子科技大学);ETH Zurich(苏黎世联邦理工学院)

Longfei Liu, Wen Guo, Shihua Huang, Cheng Li, Xi Shen

AI总结:

针对COCO数据集上目标检测器存在大量非目标背景杂波导致的假阳性问题,研究推出源自ImageNet-1K的COCO-FP评估数据集,实验显示闭集和开集场景下假阳性问题显著,为相关性能评估提供新基准。

摘要:

减少假阳性对提升目标检测器性能至关重要,这一点在平均精度均值(mAP)指标中有所体现。尽管目标检测器在COCO数据集上已取得显著提升并获得较高的mAP分数,但分析显示,在解决由非目标视觉杂波(即未被纳入标注类别的背景物体)导致的假阳性问题上进展有限。该问题在火灾烟雾检测等现实应用中尤为关键,这类场景下最大限度减少误报至关重要。本研究推出COCO-FP,这是一个源自ImageNet-1K数据集的新型评估数据集,旨在解决上述问题。通过扩展原始COCO验证集,COCO-FP专门用于评估目标检测器在抑制背景假阳性方面的性能。我们对标准和先进目标检测器的评估表明,在闭集和开集场景下都存在大量假阳性。例如,当评估基准从COCO切换到COCO-FP时,YOLOv9-E的AP50指标从72.8降至65.7。该数据集可在https://github.com/COCO-FP/COCO-FP获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑