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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

The <i>usage divide</i> of digital health technology in age-friendly home modifications: an ethnographic study among older adults in rural China.

Frontiers in public health·2026
Same author

Mapping of PTP1B, TCPTP, SHP2, and Putative Substrates Reveals Novel Networks in Glomerular Podocytes.

Journal of cellular physiology·2026
Same author

SigTime: Learning and Visually Explaining Time Series Signatures.

IEEE transactions on visualization and computer graphics·2025
Same author

ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasets.

IEEE transactions on visualization and computer graphics·2025
Same author

GSCache: Real-Time Radiance Caching for Volume Path Tracing Using 3D Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2025
Same author

Constituents from <i>Megacarpaea delavayi</i> Franch and their antimalarial activity.

Natural product research·2025
Same journal

MesoSplats: Texture Synthesis with Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

IEEE transactions on visualization and computer graphics·2026
Same journal

Multi-Perception Crowd: Learning to combine entity and implicit perception for diverse crowd simulation.

IEEE transactions on visualization and computer graphics·2026
Same journal

Hiding in Plain Sight: Camouflaging Real-world Objects.

IEEE transactions on visualization and computer graphics·2026
Same journal

RTF2Mesh: Restricted Tangent Face Based Mesh Compression With Neural Displacement Fields.

IEEE transactions on visualization and computer graphics·2026
Same journal

Practical Occluder Generation for Mobile Games.

IEEE transactions on visualization and computer graphics·2026
See all related articles

Related Experiment Video

Updated: May 24, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K

AttributionScanner: A Visual Analytics System for Model Validation With Metadata-Free Slice Finding.

Xiwei Xuan, Jorge Piazentin Ono, Liang Gou

    IEEE Transactions on Visualization and Computer Graphics
    |March 3, 2025
    PubMed
    Summary
    This summary is machine-generated.

    AttributionScanner enables metadata-free data slice finding for machine learning (ML) vision models. This human-in-the-loop visual analytics system identifies biases and errors, enhancing model reliability.

    More Related Videos

    Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
    13:35

    Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

    Published on: March 21, 2021

    10.3K
    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

    Published on: August 23, 2017

    9.8K

    Related Experiment Videos

    Last Updated: May 24, 2025

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    8.9K
    Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
    13:35

    Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

    Published on: March 21, 2021

    10.3K
    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

    Published on: August 23, 2017

    9.8K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Data slice finding validates machine learning (ML) models by analyzing subgroups with poor performance.
    • Validating vision models is challenging due to the need for metadata and difficulty interpreting performance issues.
    • Existing methods require laborious metadata collection and complex interpretation for image data.

    Purpose of the Study:

    • To introduce AttributionScanner, a novel human-in-the-loop visual analytics (VA) system for metadata-free data slice finding in ML vision models.
    • To enable efficient detection and interpretation of model performance issues like biases and mislabeled data.
    • To improve the reliability and accuracy of ML vision models through targeted issue mitigation.

    Main Methods:

    • Developed AttributionScanner, a VA system for metadata-free data slice finding.
    • Implemented an Attribution Mosaic design for visualizing common model behaviors and data slices.
    • Integrated an interactive interface for user-guided detection, interpretation, and annotation of model issues.
    • Employed a model regularization technique to address detected issues.

    Main Results:

    • AttributionScanner successfully identifies interpretable data slices without requiring additional metadata.
    • The system visualizes common model behaviors, aiding in the detection of spurious correlations and mislabeled data.
    • Evaluations on benchmark datasets demonstrate significant effectiveness in vision model validation.
    • The integrated regularization technique mitigates identified issues, enhancing model performance.

    Conclusions:

    • AttributionScanner offers an effective solution for metadata-free data slice finding in ML vision models.
    • The system facilitates the detection and resolution of common model issues, leading to improved model reliability.
    • This approach enhances the interpretability and usability of visual analytics for ML model validation.