"PatternCom"

"PatternCom is a composed image retrieval benchmark based on PatternNet. PatternNet is a large-scale high-resolution remote sensing image retrieval dataset. There are 38 classes and each class has 800 images of size 256\u00d7256 pixels. In PatternCom, we select some classes to be depicted in query images, and add a query text that defines an attribute relevant to that class. For instance, query images of \u201cswimming pools\u201d are combined with text queries defining \u201cshape\u201d as \u201crectangular\u201d, \u201coval\u201d, and \u201ckidney-shaped\u201d. In total, PatternCom includes six attributes consisted of up to four different classes each. Each attribute can be associated with two to five values per class. The number of positives ranges from 2 to 1345 and there are more than 21k queries in total."

PatternCom是一款基于PatternNet构建的组合式图像检索基准数据集。PatternNet是一款大规模高分辨率遥感图像检索数据集，共包含38个类别，每个类别配有800张分辨率为256×256像素的图像。在PatternCom中，我们选取部分类别作为查询图像的描绘对象，并添加用于定义与该类别相关属性的查询文本。例如，针对“游泳池”类别的查询图像，将与定义“形状”为“矩形”“椭圆形”及“肾形”的文本查询相结合。总体而言，PatternCom包含6类属性，每类属性最多对应4个不同的类别。每个类别针对每类属性可关联2至5个属性值。正样本的数量介于2至1345之间，且该数据集总计包含超过2.1万条查询。

搜集汇总

背景与挑战

背景概述

PatternCom是一个基于PatternNet的复合图像检索基准数据集，包含38个类别，每个类别有800张256×256像素的遥感图像，并添加了与类别相关的文本查询属性，适用于跨模态图像检索任务。