Jove
Visualize
Contact Us

Related Experiment Videos

Greedy learning of multiple objects in images using robust statistics and factorial learning.

Christopher K I Williams1, Michalis K Titsias

  • 1School of Informatics, University of Edinburgh, Edinburgh EH1 2QL, UK. c.k.i.williams@ed.ac.uk

Neural Computation
|April 9, 2004
PubMed
Summary

This study introduces a new method for object learning in images. It efficiently extracts object models sequentially, avoiding computational issues with multiple objects.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fusing Foveal Fixations Using Linear Retinal Transformations and Bayesian Experimental Design.

Neural computation·2025
Same author

Of Mice and Mates: Automated Classification and Modelling of Mouse Behaviour in Groups Using a Single Model Across Cages.

International journal of computer vision·2024
Same author

Persistent animal identification leveraging non-visual markers.

Machine vision and applications·2023
Same author

Inference and Learning for Generative Capsule Models.

Neural computation·2023
Same author

On Suspicious Coincidences and Pointwise Mutual Information.

Neural computation·2022
Same author

The Effect of Class Imbalance on Precision-Recall Curves.

Neural computation·2021
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Area of Science:

  • Computer Vision
  • Machine Learning
  • Statistical Modeling

Background:

  • Learning object models from images with multiple objects is challenging.
  • Factorial learning models face combinatorial explosion with increasing object numbers.

Purpose of the Study:

  • To develop a method for efficient object model extraction from images with multiple objects.
  • To overcome the combinatorial explosion problem in factorial learning.

Main Methods:

  • Sequential extraction of object models.
  • Utilizing a robust statistical method.
  • Addressing factorial learning challenges.

Main Results:

  • Successfully extracted object models from real-world images.

Related Experiment Videos

  • Demonstrated avoidance of combinatorial explosion.
  • Validated the effectiveness of the sequential extraction approach.

    • Conclusions:

    • The proposed method enables efficient and robust object model extraction.
    • This approach effectively handles complex image data with multiple objects.
    • Significant advancement in factorial learning for computer vision applications.