Discriminative Graphical Models For Context-Based Classification
COMPUTER VISION: DETECTION, RECOGNITION AND RECONSTRUCTION(2010)
摘要
Natural image data shows significant dependencies that should be modeled appropriately to achieve good classification. Such dependencies are commonly referred to as context in Vision. This chapter describes Conditional Random Fields (CRFs) based discriminative models for incorporating context in a principled manner. Unlike the traditional generative Markov Random Fields (MRFs), CRFs allow the use of arbitrarily complex dependencies in the observed data along with data-dependent interactions in labels. Fast and robust parameter learning techniques for such models are described. The extensions of the standard binary CRFs to handle problems with multiclass labels or hierarchical context arc also discussed. Finally, application of CRFs on contextual object detection, scene segmentation and texture recognition tasks is demonstrated.
更多查看译文
关键词
conditional random field,graphical model,discriminative model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络