CEAai/FindMeIfYouCan

FMIYC（Find Me If You Can）数据集是为了出分布（OOD）对象检测任务而设计的。它由从COCO（Common Objects in Context）和OpenImages数据集中派生和改编的图像和注释组成。FMIYC数据集将这些来源整合为新的评估分割，根据语义相似性分为近、远和更远的ID数据。这种分类允许对OOD检测模型进行细微的评估。此版本的数据集结构化为几个配置，每个配置包含图像文件和相应的metadata.jsonl文件，详细说明了这些图像的注释。

The FMIYC (Find Me If You Can) dataset is designed for Out-Of-Distribution (OOD) Object Detection tasks. It comprises images and annotations derived and adapted from the COCO (Common Objects in Context) and OpenImages datasets. The FMIYC dataset curates these sources into new evaluation splits categorized as near, far, and farther from In-Distribution (ID) data, based on semantic similarity. This categorization allows for a nuanced evaluation of OOD detection models.