Cascaded Classification Models: Combining Models for Holistic Scene Understanding
NIPS(2008)
摘要
One of the original goals of computer vision was to fully understand a natural scene. This requires solving several sub-problems simulta neously, including ob- ject detection, region labeling, and geometric reasoning. The last few decades have seen great progress in tackling each of these problems i n isolation. Only re- cently have researchers returned to the difficult task of con sidering them jointly. In this work, we consider learning a set of related models in suc h that they both solve their own problem and help each other. We develop a framework called Cascaded Classification Models ( CCM), where repeated instantiations of these classifiers are coupled by their input/output variables in a cascade tha t improves performance at each level. Our method requires only a limited "black box" interface with the models, allowing us to use very sophisticated, state-of-th e-art classifiers without having to look under the hood. We demonstrate the effectiveness of our method on a large set of natural images by combining the subtasks of scene categorization, object detection, multiclass image segmentation, and 3d reconstruction.
更多查看译文
关键词
relational model,image segmentation,computer vision,3d reconstruction,input output
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络