首页> 外文期刊>Pattern Analysis and Machine Intelligence, IEEE Transactions on >Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)
【24h】

Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)

机译:混合图模型(HGM)的无监督对象分割

获取原文
获取原文并翻译 | 示例

摘要

In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmentation can be regarded as a special data clustering problem where both class-specific information and local texture/color similarities have to be considered. To this end, we propose a hybrid graph model (HGM) that can make effective use of both symmetric and asymmetric relationship among samples. The vertices of a hybrid graph represent the samples and are connected by directed edges and/or undirected ones, which represent the asymmetric and/or symmetric relationship between them, respectively. When applied to object segmentation, vertices are superpixels, the asymmetric relationship is the conditional dependence of occurrence, and the symmetric relationship is the color/texture similarity. By combining the Markov chain formed by the directed subgraph and the minimal cut of the undirected subgraph, the object boundaries can be determined for each image. Using the HGM, we can conveniently achieve simultaneous segmentation and recognition by integrating both top-down and bottom-up information into a unified process. Experiments on 42 object classes (9,415 images in total) show promising results.
机译:在这项工作中,我们解决了执行特定于类的无监督对象分割问题,即没有注释训练图像的自动分割。对象分割可以看作是一个特殊的数据聚类问题,其中必须同时考虑类特定信息和局部纹理/颜色相似性。为此,我们提出了一种混合图模型(HGM),该模型可以有效利用样本之间的对称和非对称关系。混合图的顶点表示样本,并通过有向边和/或无向边连接,分别代表它们之间的不对称和/或对称关系。当应用于对象分割时,顶点是超像素,不对称关系是出现的条件依赖性,而对称关系是颜色/纹理相似度。通过组合由有向子图形成的马尔可夫链和无向子图的最小割,可以为每个图像确定对象边界。使用HGM,我们可以通过将自上而下和自下而上的信息集成到一个统一的过程中,方便地实现同时的分割和识别。在42种物体类别(总共9,415张图像)上进行的实验显示出令人鼓舞的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号