Multiple-Instance Learning for Natural Scene Classification
Multiple-Instance Learning for Natural Scene Classification
复制标题
DOI：
--
复制
发表时间：
1998-07
期刊：
影响因子：
--
通讯作者：
O. Maron;A. L. Ratan
中科院分区：
文献类型：
--
作者：
O. Maron;A. L. Ratan
我们研究了一种用于学习简单模板的称为多构度学习的方法，该模板从一小部分示例中捕获了自然场景图像的颜色和空间特性。这些模板将场景类编码为带有颜色和空间关系的图像补丁，可用于对各种自然场景进行分类，例如Elds，Waterfalls和Mountains。示例图像是模棱两可的，因为有许多可能的模板可以描述单个图像。多种现实学习使歧义明确，我们讨论了从模棱两可的示例中学习的一种多样性密度算法。该系统使用非常低的分辨率图像从一组示例中提取模板。一旦学习了模板，我们就会使用Corel照片库来测试其检索率和准确性。我们证明非常简单的模板是Suu-Cient，并且通过更多的用户互动来提高性能。
We investigate a method called Multiple-Instance learning for learning simple templates that capture the color and spatial properties of classes of natural scene images from a small set of examples. These templates encode a scene class as image patches with color and spatial relations and can be used to classify a variety of natural scenes like elds, waterfalls and mountains among others. Example images are ambiguous since there are many possible templates that can describe an individual image. Multiple-Instance learning makes the ambiguity explicit, and we discuss the Diverse Density algorithm which is a method of learning from ambiguous examples. The system uses very low resolution images to extract the templates from a set of examples. Once a template is learned, we use the COREL photo library to test its retrieval rates and accuracy. We show that very simple templates are suu-cient, and that performance improves with more user interaction.