Stacked Hierarchical Labeling
Stacked Hierarchical Labeling
复制标题
DOI：
10.1007/978-3-642-15567-3_5
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Daniel Munoz;J. Bagnell;Martial Hebert
中科院分区：
文献类型：
--
作者：
Daniel Munoz;J. Bagnell;Martial Hebert
在这项工作中，我们提出了一个分层的方法来标记场景中的语义对象和区域。我们的方法让人想起早期的视觉文献，因为我们使用的图像的分解，以编码的关系和空间信息。与现有的许多用于场景理解的结构化预测工作相比，我们绕过了全局概率模型，而是直接训练了一个层次推理程序，该程序受到图形模型中一些近似推理程序的消息传递机制的启发。这种方法减轻了学习概率模型的理论和经验困难时，精确的推理是棘手的。特别是，我们借鉴了机器学习的最新研究成果，将复杂的推理过程分解为一系列简单的机器学习子问题。层次结构中的每个子问题被设计为捕获场景中的图像和上下文统计。该层次结构跨越从粗到细的区域，并明确地对由于不完美分割而可能存在的语义标签的混合物进行建模。为了避免级联错误和过拟合，我们按顺序训练学习问题，以确保对推理序列中早期可能错误的鲁棒性，并利用Cohenet al
In this work we propose a hierarchical approach for labeling semantic objects and regions in scenes. Our approach is reminiscent of early vision literature in that we use a decomposition of the image in order to encode relational and spatial information. In contrast to much existing work on structured prediction for scene understanding, we bypass a global probabilistic model and instead directly train a hierarchical inferenceprocedureinspired by the message passing mechanics of some approximate inference procedures in graphical models. This approach mitigates both the theoretical and empirical difficulties of learning probabilistic models when exact inference is intractable. In particular, we draw from recent work in machine learning and break the complex inference process into a hierarchical series of simple machine learning subproblems. Each subproblem in the hierarchy is designed to capture the image and contextual statistics in the scene. This hierarchy spans coarse-to-fine regions and explicitly models the mixtures of semantic labels that may be present due to imperfect segmentation. To avoid cascading of errors and overfitting, we train the learning problems in sequence to ensure robustness to likely errors earlier in the inference sequence and leverage the stacking approach developed by Cohenet al