Learning Hierarchical Models of Scenes, Objects, and Parts
Abstract
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model's structure to analytically average over many parameters. Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available. We also extend this hierarchical framework to scenes containing multiple objects
Cite
Text
Sudderth et al. "Learning Hierarchical Models of Scenes, Objects, and Parts." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.137Markdown
[Sudderth et al. "Learning Hierarchical Models of Scenes, Objects, and Parts." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/sudderth2005iccv-learning/) doi:10.1109/ICCV.2005.137BibTeX
@inproceedings{sudderth2005iccv-learning,
title = {{Learning Hierarchical Models of Scenes, Objects, and Parts}},
author = {Sudderth, Erik B. and Torralba, Antonio and Freeman, William T. and Willsky, Alan S.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2005},
pages = {1331-1338},
doi = {10.1109/ICCV.2005.137},
url = {https://mlanthology.org/iccv/2005/sudderth2005iccv-learning/}
}