ML Anthology

Visual Learning by Evolutionary Feature Synthesis

Krzysztof Krawiec, Bir Bhanu
ICML 2003 pp. 376-383
/icml/2003/krawiec2003icml-visual/

Abstract

In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition task. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically. The training consists in coevolving feature extraction procedures, each being a sequence of elementary image processing and feature extraction operations. Extensive experimental results show that the approach attains competitive performance for 3-D object recognition in real synthetic aperture radar (SAR) imagery. ICML Proceedings of the Twentieth International Conference on Machine Learning

PDF ICML Semantic Scholar

Cite

Text

Krawiec and Bhanu. "Visual Learning by Evolutionary Feature Synthesis." International Conference on Machine Learning, 2003.

Markdown

[Krawiec and Bhanu. "Visual Learning by Evolutionary Feature Synthesis." International Conference on Machine Learning, 2003.](https://mlanthology.org/icml/2003/krawiec2003icml-visual/)

BibTeX

@inproceedings{krawiec2003icml-visual,
  title     = {{Visual Learning by Evolutionary Feature Synthesis}},
  author    = {Krawiec, Krzysztof and Bhanu, Bir},
  booktitle = {International Conference on Machine Learning},
  year      = {2003},
  pages     = {376-383},
  url       = {https://mlanthology.org/icml/2003/krawiec2003icml-visual/}
}