Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

A three-factor nomogram predicts the use of invasive mechanical ventilation within 72 h in preterm infants.

Frontiers in medicine·2026

Same author

Membrane protein-targeted and dual-miRNAs-activated DNA quadrilateral sensor for accurate tumor cell identification.

Talanta·2026

Same author

Electrostatic complementarity and interlayer coupling modulation in halogen-modified covalent organic frameworks for enhanced photocatalytic oxygen reduction.

Journal of colloid and interface science·2026

Same author

VCAN promotes the progression and recurrence of esophageal squamous cell carcinoma by remodeling the tumor microenvironment.

Scientific reports·2026

Same author

AI-Based Virtual Standardized Patients Improve Oral Mucosal Disease Training in Fourth-Year Dental Students.

Journal of dental education·2026

Same author

Enhancing Synthesis Efficiency in Microbial 1,5-Pentanediol Production Through Transcriptomics-Informed Metabolic Engineering of <i>Escherichia coli</i>.

Microorganisms·2026

Same journal

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

Same journal

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

Same journal

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

Same journal

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

Same journal

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

Same journal

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Hyperspectral Image Classification With Multi-Attention Transformer and Adaptive Superpixel Segmentation-Based Active

Chunhui Zhao, Boao Qin, Shou Feng

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|June 27, 2023

Summary

This summary is machine-generated.

This study introduces a new hyperspectral image classification framework using a multi-attention Transformer (MAT) and active learning (AL) with adaptive superpixels. This approach excels at capturing both local and long-range features, especially with limited labeled data.

More Related Videos

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

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

Published on: April 21, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

Published on: April 21, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Remote Sensing
Computer Vision
Machine Learning

Background:

Deep learning methods like CNNs struggle with long-range feature extraction in hyperspectral images.
Acquiring sufficient labeled samples for hyperspectral image classification is costly and time-consuming.
Existing methods often fail to balance local and global feature extraction effectively.

Purpose of the Study:

To develop a hyperspectral image classification framework that effectively extracts both local and long-range spectral-spatial features.
To address the challenge of limited labeled samples in hyperspectral image classification.
To improve the efficiency and accuracy of active learning for hyperspectral image classification.

Main Methods:

A multi-attention Transformer (MAT) network was designed to model long-range dependencies and capture local features using self-attention and outlook-attention modules.
An active learning (AL) strategy based on adaptive superpixel segmentation was developed to select informative samples for training.
Adaptive superpixel segmentation was employed to preserve edge details and integrate local spatial similarity into the active learning process.

Main Results:

The proposed MAT-ASSAL framework achieved excellent classification performance, particularly with small sample sizes.
The multi-attention Transformer effectively captured both local and long-range spectral-spatial contextual dependencies.
The adaptive superpixel segmentation enhanced the active learning strategy by providing better local spatial constraints.

Conclusions:

The MAT-ASSAL framework offers a robust solution for hyperspectral image classification, outperforming state-of-the-art methods.
The integration of multi-attention Transformer and adaptive superpixel-based active learning is highly effective for scenarios with limited labeled data.
This approach demonstrates significant potential for advancing hyperspectral image analysis and classification.