Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks.
Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks.
复制标题
DOI：
10.1109/iccv.2013.269
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Tasdizen T
中科院分区：
文献类型：
--
作者：
Seyedhosseini M;Sajjadi M;Tasdizen T
背景信息在解决图像分割等视觉问题中起着重要的作用。然而，提取上下文信息并以有效的方式使用它仍然是一个难题。为了解决这一挑战，我们提出了一个多分辨率的上下文框架，称为级联层次模型（CHM），它学习上下文信息的图像分割的层次框架。在层次结构的每个级别，基于下采样的输入图像和先前级别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纳入分类器中，以原始分辨率分割输入图像。我们重复这个过程，通过级联的分层框架，以提高分割精度。在CHM中学习多个分类器;因此，需要快速准确的分类器来使训练易于处理。由于在训练期间学习的大量参数，分类器还需要对过拟合具有鲁棒性。我们介绍了一种新的分类方案，称为逻辑析取正常网络（LDNN），它由一个自适应层的特征检测器实现的逻辑sigmoid函数，其次是两个固定层的逻辑单元，计算合取和析取，分别。我们证明，LDNN优于国家的最先进的分类器，可以用于CHM，以提高对象分割性能。
Contextual information plays an important role in solving vision problems such as image segmentation. However, extracting contextual information and using it in an effective way remains a difficult problem. To address this challenge, we propose a multi-resolution contextual framework, called cascaded hierarchical model (CHM), which learns contextual information in a hierarchical framework for image 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. We repeat this procedure by cascading the hierarchical framework to improve the segmentation accuracy. Multiple classifiers are learned in the CHM; therefore, a fast and accurate classifier is required to make the training tractable. The classifier also needs to be robust against overfitting due to the large number of parameters learned during training. We introduce a novel classification scheme, called logistic disjunctive normal networks (LDNN), which consists of one adaptive layer of feature detectors implemented by logistic sigmoid functions followed by two fixed layers of logical units that compute conjunctions and disjunctions, respectively. We demonstrate that LDNN outperforms state-of-theart classifiers and can be used in the CHM to improve object segmentation performance.