NAO自然界对抗样本数据集

DESCRIPTIONWe introduce a new dataset, Natural Adversarial Objects (NAO), to evaluate the robustness of object detection models. NAO contains 7,934 images and 9,943 objects that are unmodified and representative of real-world scenarios, but cause state-of-the-art detection models to misclassify with high confidence. The mean average precision (mAP) of EfficientDet-D7 drops 74.5% when evaluated on NAO compared to the standard MSCOCO validation set.PUBLICATIONSNatural Adversarial Objectsinsert_drive_file

### 数据集说明
我们推出了全新数据集**自然对抗目标数据集（Natural Adversarial Objects, NAO）**，用于评估目标检测模型的鲁棒性。该数据集包含7934张图像与9943个未经过修改、具有真实场景代表性的目标，但会使当前前沿的目标检测模型以高置信度发生误分类。与标准MSCOCO验证集相比，EfficientDet-D7在该数据集上的平均精度均值（mean average precision, mAP）下降了74.5%。
### 相关出版物
Natural Adversarial Objects

搜集汇总

背景与挑战

背景概述

NAO自然界对抗样本数据集包含7,934张真实场景图片和9,943个对象，用于测试目标检测模型的鲁棒性，能显著降低先进模型的检测精度（如EfficientDet-D7的mAP下降74.5%）。数据集由Scale AI提供，文件格式为zip，大小799.09MB。