Jove
Visualize
Contact Us
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

Related Experiment Videos

MILES: multiple-instance learning via embedded instance selection.

Yixin Chen1, Jinbo Bi, James Z Wang

  • 1Department of Computer and Information Science, Universit of Mississippi, MS 38677, USA. ychen@cs.olemiss.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 17, 2006
PubMed
Summary
This summary is machine-generated.

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

Mapping the flow of painterly gesture.

Patterns (New York, N.Y.)·2026
Same author

S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same author

Applying AI models to digital placental photographs to automate and improve morphology assessments.

medRxiv : the preprint server for health sciences·2026
Same author

Computational Investigation of Abstraction in Claude Monet's Water Lilies Through Brushstroke Analysis.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

SHAP-based explainable machine learning analysis of reward-related neural connectivity to predict preadolescent irritability.

Neuroimage. Reports·2026
Same author

Blood Metabolomic and Proteomic Signatures of Total, Healthy, and Unhealthy Low-Carbohydrate Diets in the UK Biobank.

Journal of the American Nutrition Association·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces MILES, a novel multiple-instance learning method that bypasses restrictive assumptions. MILES effectively handles complex data by converting problems into supervised learning tasks, improving classification accuracy.

Area of Science:

  • Machine Learning
  • Computer Vision
  • Pattern Recognition

Background:

  • Multiple-instance learning (MIL) assigns labels to bags of instances.
  • Traditional MIL assumes a bag is positive if at least one instance is positive.
  • This assumption limits applicability, especially in computer vision.

Purpose of the Study:

  • To develop a flexible MIL algorithm that does not rely on restrictive assumptions.
  • To improve classification accuracy and efficiency in MIL tasks.
  • To address limitations of existing MIL methods in computer vision.

Main Methods:

  • Proposed MILES (Multiple-Instance Learning via Embedded instance Selection) algorithm.
  • Converted MIL to a standard supervised learning problem.

Related Experiment Videos

  • Utilized instance similarity for feature space mapping and 1-norm SVM for feature selection and classification.

    • Main Results:

    • MILES demonstrated competitive classification accuracy compared to existing methods.
    • The algorithm exhibited high computational efficiency.
    • MILES showed robustness to labeling uncertainty in experiments.

    Conclusions:

    • MILES offers a flexible and effective approach to multiple-instance learning.
    • The method overcomes limitations of traditional MIL assumptions.
    • MILES provides a promising solution for various applications, including computer vision.