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

Dominant Sets for "Constrained" Image Segmentation.

Eyasu Zemene, Leulseged Tesfaye Alemu, Marcello Pelillo

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |July 25, 2018
    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

    Vector Flows That Compute the Capacity of Discrete Memoryless Channels.

    Entropy (Basel, Switzerland)·2025
    Same author

    The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning.

    IEEE transactions on pattern analysis and machine intelligence·2022
    Same author

    Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges.

    IEEE transactions on pattern analysis and machine intelligence·2021
    Same author

    LiSSA: Localized Stochastic Sensitive Autoencoders.

    IEEE transactions on cybernetics·2019
    Same author

    A Functional Representation for Graph Matching.

    IEEE transactions on pattern analysis and machine intelligence·2019
    Same author

    Large-Scale Image Geo-Localization Using Dominant Sets.

    IEEE transactions on pattern analysis and machine intelligence·2018
    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 a unified approach for constrained image segmentation, including interactive segmentation and co-segmentation. The method uses dominant sets and a regularization parameter to effectively handle various constraints and noisy user input.

    Area of Science:

    • Computer Vision
    • Graph Theory
    • Optimization

    Background:

    • Image segmentation remains a challenging problem in computer vision.
    • Existing methods often require user assistance (interactive segmentation) or simultaneous segmentation of multiple images (co-segmentation).
    • These variants can be viewed as constrained versions of image segmentation, guided by external information.

    Purpose of the Study:

    • To propose a unified approach for constrained image segmentation problems.
    • To leverage properties of dominant sets and quadratic optimization for segmentation.
    • To develop a method capable of handling interactive segmentation and co-segmentation.

    Main Methods:

    • Utilized properties of quadratic optimization problems related to dominant sets.

    Related Experiment Videos

  • Introduced a controllable regularization parameter to define problem structure and scale.
  • Developed an algorithm to extract dominant-set clusters constrained by predefined elements.

    • Main Results:

    • Demonstrated the ability to extract constrained dominant-set clusters.
    • Showcased the algorithm's effectiveness in handling interactive segmentation and co-segmentation (unsupervised and interactive).
    • Validated the approach's robustness with various constraints (scribbles, contours, bounding boxes) and noisy user annotations.

    Conclusions:

    • The proposed method offers a unified framework for diverse constrained image segmentation tasks.
    • The algorithm effectively handles multiple constraint types and input modalities.
    • Experimental results confirm the approach's superior performance compared to state-of-the-art methods on benchmark datasets.