Scene Segmentation with CRFs Learned from Partially Labeled Images
Scene Segmentation with CRFs Learned from Partially Labeled Images
复制标题
DOI：
--
复制
发表时间：
2007-12
期刊：
影响因子：
--
通讯作者：
J. Verbeek;B. Triggs
中科院分区：
文献类型：
--
作者：
J. Verbeek;B. Triggs
条件随机场（CRFs）是一种有效的工具，用于各种不同的数据分割和标记任务，包括视觉场景解释，它试图将图像划分为其组成的语义级区域，并为每个区域分配适当的类标签。为了准确标记，重要的是要捕获图像的全局上下文以及局部信息。我们引入了一种基于CRF的场景标记模型，该模型结合了局部特征和在整个图像或大部分图像上聚集的特征。其次，传统的CRF学习需要完全标记的数据集，这可能是昂贵的和麻烦的。我们介绍了一种方法，用于从具有许多未标记节点的数据集中学习CRF，通过边缘化未知标签，使得已知标签的对数似然性可以通过梯度上升来最大化。循环置信传播用于近似梯度和对数似然计算所需的边缘，并且监测对数似然的Bethe自由能近似以控制步长。我们的实验结果表明，有效的模型可以从零碎的标签，并纳入自上而下的聚合功能显着提高了分割。将所得分割与三个不同图像数据集上的最新技术进行比较。
Conditional Random Fields (CRFs) are an effective tool for a variety of different data segmentation and labeling tasks including visual scene interpretation, which seeks to partition images into their constituent semantic-level regions and assign appropriate class labels to each region. For accurate labeling it is important to capture the global context of the image as well as local information. We introduce a CRF based scene labeling model that incorporates both local features and features aggregated over the whole image or large sections of it. Secondly, traditional CRF learning requires fully labeled datasets which can be costly and troublesome to produce. We introduce a method for learning CRFs from datasets with many unlabeled nodes by marginalizing out the unknown labels so that the log-likelihood of the known ones can be maximized by gradient ascent. Loopy Belief Propagation is used to approximate the marginals needed for the gradient and log-likelihood calculations and the Bethe free-energy approximation to the log-likelihood is monitored to control the step size. Our experimental results show that effective models can be learned from fragmentary labelings and that incorporating top-down aggregate features significantly improves the segmentations. The resulting segmentations are compared to the state-of-the-art on three different image datasets.