ECSSD

Although images from MSRA-1000 have a large variety in their content, background structures are primarily simple and smooth. To represent the situations that natural images generally fall into, we extend our Complex Scene Saliency Dataset (CSSD) in a larger dataset (ECSSD) with 1000 images, which includes many semantically meaningful but structurally complex images for evaluation. The images are acquired from the internet and 5 helpers were asked to produce the ground truth masks. Several examples with their corresponding masks are shown above.

尽管MSRA-1000数据集的图像内容丰富多样，但其背景结构整体简洁平滑。为了还原自然图像普遍存在的场景分布，我们将自身研发的复杂场景显著性数据集（Complex Scene Saliency Dataset，CSSD）扩展为规模更大的ECSSD数据集，该数据集共包含1000张图像，收录了大量兼具语义价值与结构复杂性的图像用于评测。该数据集的所有图像均采集自互联网，并邀请5名标注人员完成了真值掩码（ground truth masks）的标注工作。上文展示了若干带有对应掩码的图像示例。

搜集汇总

背景与挑战

背景概述

ECSSD是一个包含1000张复杂场景图像的显著性检测数据集，图像具有丰富的语义内容和复杂的结构，适用于自然图像的显著性评估。数据集通过互联网收集，并由多名助手标注真实掩码。