tiiuae/PBench

PBench是一个感知基准测试数据集，专门用于引用表达式分割任务。该数据集旨在通过结构化技能层次评估视觉语言感知能力，帮助诊断模型在不同感知技能上的表现。数据集包含6,338个样本，覆盖83,977个实例掩码和5,090个独特表达式，分为五个级别和一个密集分割：Level 0（通用对象类别，测试基本对象识别和掩码质量）、Level 1（细粒度属性和子类型，测试属性使用）、Level 2（文本作为标识符，测试OCR能力）、Level 3（空间关系和布局，测试空间推理）、Level 4（关系和交互，测试对象间理解）以及密集分割（密集实例分割，测试在拥挤场景中的分割能力）。每个样本包含图像、引用表达式、掩码列表和掩码数量等字段，适用于图像分割和自然语言处理研究。

PBench is a perception benchmark for referring expression segmentation, designed to evaluate vision-language perception across a structured hierarchy of skills. The dataset contains 6,338 samples with 83,977 instance masks and 5,090 unique expressions, organized into five levels plus a dense split: Level 0 (general object classes, testing basic object recognition and mask quality), Level 1 (fine-grained attributes and subtypes, testing attribute usage), Level 2 (text as identifier, testing OCR capability), Level 3 (spatial relationships and layout, testing spatial reasoning), Level 4 (relationships and interactions, testing inter-object understanding), and the dense split (dense instance segmentation, testing segmentation in crowded scenes). Each sample includes fields such as image, referring expression, list of masks, and mask count, making it suitable for image segmentation and natural language processing research.