Cascaded Classification Models: Combining Models for Holistic Scene Understanding
Date
2008
Authors
Geremy, Heitz
Gould, Stephen
Saxena, Ashutosh
Koller, Daphne
Journal Title
Journal ISSN
Volume Title
Publisher
MIT Press
Abstract
One of the original goals of computer vision was to fully understand a natural scene. This requires solving several sub-problems simultaneously, including object detection, region labeling, and geometric reasoning. The last few decades have seen great progress in tackling each of these problems in isolation. Only recently have researchers returned to the difficult task of considering them jointly. In this work, we consider learning a set of related models in such 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 that 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-the-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.
Description
Keywords
Keywords: 3D reconstruction; Black boxes; Cascaded classification; Combining model; Geometric reasoning; Input/output; Multi-class; Natural images; Natural scenes; Object Detection; Region labeling; Scene categorization; Scene understanding; Sub-problems; Subtasks;
Citation
Collections
Source
Advances in Neural Information Processing Systems 21
Type
Conference paper
Book Title
Entity type
Access Statement
License Rights
DOI
Restricted until
2037-12-31
Downloads
File
Description