Semantic Image Segmentation with Contextual Hierarchical Models.
Semantic Image Segmentation with Contextual Hierarchical Models.
复制标题
DOI：
10.1109/tpami.2015.2473846
复制
发表时间：
2016-05
影响因子：
23.6
通讯作者：
Tasdizen T
中科院分区：
文献类型：
--
作者：
Seyedhosseini M;Tasdizen T
语义分割是为每个像素分配对象标签的问题。它将图像分割和目标识别问题统一起来。在语义切分框架中使用上下文信息的重要性已经在该领域得到了广泛的认识。我们提出了一个上下文框架，称为上下文层次模型(CHM)，它在一个用于语义分割的层次框架中学习上下文信息。在层级的每一级，基于下采样的输入图像和先前级的输出来训练分类器。然后，我们的模型将得到的多分辨率上下文信息合并到分类器中，以原始分辨率分割输入图像。该训练策略允许通过分层结构在多个分辨率下优化联合后验概率。上下文层次模型纯粹基于输入图像块，不使用任何片段或形状示例。因此，它适用于目标分割、边缘检测等多种问题。我们证明了CHM在斯坦福背景和魏茨曼马数据集上的表现与最先进的水平相当。它在NYU深度数据集上的性能也优于最先进的边缘检测方法，在Berkeley分割数据集(BSDS 500)上也达到了最先进的边缘检测方法。
Semantic segmentation is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in semantic segmentation frameworks has been widely realized in the field. We propose a contextual framework, called contextual hierarchical model (CHM), which learns contextual information in a hierarchical framework for semantic segmentation. At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels. Our model then incorporates the resulting multi-resolution contextual information into a classifier to segment the input image at original resolution. This training strategy allows for optimization of a joint posterior probability at multiple resolutions through the hierarchy. Contextual hierarchical model is purely based on the input image patches and does not make use of any fragments or shape examples. Hence, it is applicable to a variety of problems such as object segmentation and edge detection. We demonstrate that CHM performs at par with state-of-the-art on Stanford background and Weizmann horse datasets. It also outperforms state-of-the-art edge detection methods on NYU depth dataset and achieves state-of-the-art on Berkeley segmentation dataset (BSDS 500).