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

Underdetermined Blind Source Separation via Weighted Simplex Shrinkage Regularization and Quantum Deep Image Prior.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Microscopic-based analysis of nuclei in spheroids via SUNSHINE: An on-chip workflow integrating optical clearing, fluorescence calibration and supervoxel segmentation.

Computers in biology and medicine·2025
Same author

Endangered Black-faced Spoonbills alter migration across the Yellow Sea due to offshore wind farms.

Ecology·2024
Same author

Metasurface-empowered snapshot hyperspectral imaging with convex/deep (CODE) small-data learning theory.

Nature communications·2023
Same author

Hyperspectral Tensor Completion Using Low-Rank Modeling and Convex Functional Analysis.

IEEE transactions on neural networks and learning systems·2023
Same author

The Risk Factors for Radiolucent Nephrolithiasis among Workers in High-Temperature Workplaces in the Steel Industry.

International journal of environmental research and public health·2022

Related Experiment Video

Updated: Jun 15, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.3K

Unsupervised Abundance Matrix Reconstruction Transformer-Guided Fractional Attention Mechanism for Hyperspectral

Si-Sheng Young, Chia-Hsiang Lin, Zi-Chao Leng

    IEEE Transactions on Neural Networks and Learning Systems
    |August 28, 2024
    PubMed
    Summary

    This study introduces a new hyperspectral anomaly detection (HAD) method using transformer-guided fractional attention within the abundance domain (TGFA-AD). TGFA-AD enhances detection accuracy by reconstructing abundance matrices and employing novel attention mechanisms.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    379
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.8K

    Related Experiment Videos

    Last Updated: Jun 15, 2025

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
    08:47

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

    Published on: February 9, 2024

    1.3K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    379
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.8K

    Area of Science:

    • Remote Sensing
    • Computer Vision
    • Signal Processing

    Background:

    • Hyperspectral anomaly detection (HAD) is crucial for identifying rare targets in hyperspectral imagery.
    • Existing HAD methods struggle with low spatial resolution and incomplete anomaly removal in residual-based frameworks.

    Purpose of the Study:

    • To propose a novel HAD method, transformer-guided fractional attention within the abundance domain (TGFA-AD), to address limitations of current algorithms.
    • To improve the distinction between normal and abnormal pixels and ensure complete anomaly effect removal.

    Main Methods:

    • Utilized blind source separation (BSS) to obtain abundance matrices, replacing raw hyperspectral images.
    • Developed an abundance spatial-channel reconstruction transformer (ASCR-Former) for abundance matrix rebuilding.
    • Introduced a fractional abundance attention (FAA) mechanism guided by initial detection and incorporated fractional convolution for final detection.

    Main Results:

    • The proposed ASCR-Former effectively reconstructs abundance matrices by encoding patch-wise abundance with CLS tokens.
    • The FAA mechanism and fractional convolution successfully fuse abundance and residual information for enhanced detection.
    • TGFA-AD demonstrated state-of-the-art performance in quantitative and qualitative real-data experiments.

    Conclusions:

    • TGFA-AD offers a significant advancement in hyperspectral anomaly detection by operating in the abundance domain.
    • The novel attention and reconstruction mechanisms effectively overcome the limitations of existing HAD approaches.
    • The proposed method shows superior performance for identifying anomalies in hyperspectral images.