ML Anthology

Coevolutionary Computation for Synthesis of Recognition Systems

Krzysztof Krawiec, Bir Bhanu
CVPRW 2003 pp. 59
doi:10.1109/CVPRW.2003.10061 /cvprw/2003/krawiec2003cvprw-coevolutionary/

Abstract

This paper introduces a novel visual learning method that involves cooperative coevolution and linear genetic programming. Given exclusively training images, the evolutionary learning algorithm induces a set of sophisticated feature extraction agents represented in a procedural way. The proposed method incorporates only general vision-related background knowledge and does not require any task-specific information. The paper describes the learning algorithm, provides a firm rationale for its design, and proves its competitiveness with the human-designed recognition systems in an extensive experimental evaluation, on the demanding real-world task of object recognition in synthetic aperture radar (SAR) imagery.

CVPRW Semantic Scholar

Cite

Text

Krawiec and Bhanu. "Coevolutionary Computation for Synthesis of Recognition Systems." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003. doi:10.1109/CVPRW.2003.10061

Markdown

[Krawiec and Bhanu. "Coevolutionary Computation for Synthesis of Recognition Systems." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003.](https://mlanthology.org/cvprw/2003/krawiec2003cvprw-coevolutionary/) doi:10.1109/CVPRW.2003.10061

BibTeX

@inproceedings{krawiec2003cvprw-coevolutionary,
  title     = {{Coevolutionary Computation for Synthesis of Recognition Systems}},
  author    = {Krawiec, Krzysztof and Bhanu, Bir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2003},
  pages     = {59},
  doi       = {10.1109/CVPRW.2003.10061},
  url       = {https://mlanthology.org/cvprw/2003/krawiec2003cvprw-coevolutionary/}
}