VIP内容
在人工智能、统计学、计算机系统、计算机视觉、自然语言处理和计算生物学等许多领域中，许多问题都可以被视为从局部信息中寻找一致的全局结论。概率图模型框架为这一范围广泛的问题提供了一个统一的视图，能够在具有大量属性和巨大数据集的问题中进行有效的推理、决策和学习。这门研究生水平的课程将为您在复杂问题中运用图模型中解决核心研究主题提供坚实的基础。本课程将涵盖三个方面: 核心表示，包括贝叶斯网络和马尔科夫网络，以及动态贝叶斯网络;概率推理算法，包括精确和近似; 以及图模型的参数和结构的学习方法。进入这门课程的学生应该预先具备概率、统计学和算法的工作知识，尽管这门课程的设计是为了让有较强数学背景的学生赶上并充分参与。希望通过本课程的学习，学生能够获得足够的实际应用的多变量概率建模和推理的工作知识，能够用通用模型在自己的领域内制定和解决广泛的问题。并且可以自己进入更专业的技术文献。
成为VIP会员查看完整内容
Lecture 1 : Course Introduction
Lecture 2 : Directed Graphical Models: Bayesian Networks
Lecture 3 : Undirected Graphical Models: Markov Random Fields & Conditional Random Fields
Lecture 4 : Markov Properties / Factor Graphs
Lecture 5 : Exact Marginal/MAP Inference: Variable Elimination & Belief Propagation
Lecture 6 : Learning fully observable MRFs and CRFs
Lecture 7 : Neural Potential Functions
Lecture 8 : Hybrids of Neural Nets and Graphical Models / Recurrent neural networks (RNNs) / LP, ILP, and MILP
Lecture 9 : MAP Inference: Mixed Integer Linear Programming
Lecture 10 : Structured Perceptron / Structured SVM
Lecture 11 : Convolutional neural networks (CNNs)
Lecture 12 : Complexity of Inference / Monte Carlo Methods
Lecture 13 : Markov Chain Monte Carlo: Gibbs Sampling & Metropolis-Hastings
热门内容
最新内容
Dense disparities among multiple views is essential for estimating the 3D architecture of a scene based on the geometrical relationship among the scene and the views or cameras. Scenes with larger extents of heterogeneous textures, differing scene illumination among the multiple views and with occluding objects affect the accuracy of the estimated disparities. Markov random fields (MRF) based methods for disparity estimation address these limitations using spatial dependencies among the observations and among the disparity estimates. These methods, however, are limited by spatially fixed and smaller neighborhood systems or cliques. In this work, we present a new factor graph-based probabilistic graphical model for disparity estimation that allows a larger and a spatially variable neighborhood structure determined based on the local scene characteristics. We evaluated our method using the Middlebury benchmark stereo datasets and the Middlebury evaluation dataset version 3.0 and compared its performance with recent state-of-the-art disparity estimation algorithms. The new factor graph-based method provided disparity estimates with higher accuracy when compared to the recent non-learning- and learning-based disparity estimation algorithms. In addition to disparity estimation, our factor graph formulation can be useful for obtaining maximum a posteriori solution to optimization problems with complex and variable dependency structures as well as for other dense estimation problems such as optical flow estimation.
最新论文
Dense disparities among multiple views is essential for estimating the 3D architecture of a scene based on the geometrical relationship among the scene and the views or cameras. Scenes with larger extents of heterogeneous textures, differing scene illumination among the multiple views and with occluding objects affect the accuracy of the estimated disparities. Markov random fields (MRF) based methods for disparity estimation address these limitations using spatial dependencies among the observations and among the disparity estimates. These methods, however, are limited by spatially fixed and smaller neighborhood systems or cliques. In this work, we present a new factor graph-based probabilistic graphical model for disparity estimation that allows a larger and a spatially variable neighborhood structure determined based on the local scene characteristics. We evaluated our method using the Middlebury benchmark stereo datasets and the Middlebury evaluation dataset version 3.0 and compared its performance with recent state-of-the-art disparity estimation algorithms. The new factor graph-based method provided disparity estimates with higher accuracy when compared to the recent non-learning- and learning-based disparity estimation algorithms. In addition to disparity estimation, our factor graph formulation can be useful for obtaining maximum a posteriori solution to optimization problems with complex and variable dependency structures as well as for other dense estimation problems such as optical flow estimation.
