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

Feature Enhancement Module Based on Class-Centric Loss for Fine-Grained Visual Classification.

IEEE transactions on neural networks and learning systems·2025

Same author

Leveraging Predictions of Task-Related Latents for Interactive Visual Navigation.

IEEE transactions on neural networks and learning systems·2023

Same author

Lotus-Root-Like Carbon Fibers Embedded with Ni-Co Nanoparticles for Dendrite-Free Lithium Metal Anodes.

Advanced materials (Deerfield Beach, Fla.)·2021

Same author

The relationship between COVID-19's severity and ischemic stroke: a systematic review and meta-analysis.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2021

Same author

Cerebroprotection by dioscin after experimental subarachnoid haemorrhage via inhibiting NLRP3 inflammasome through SIRT1-dependent pathway.

British journal of pharmacology·2021

Same author

High-yield purification of exceptional-quality, single-molecule DNA substrates.

Journal of biological methods·2021

Same journal

BPENet: Boundary perception enhancement network for retinal vessel and coronary angiogram segmentation.

Journal of X-ray science and technology·2026

Same journal

Semi-supervised YOLO-DEP for high-resolution X-ray component localization and counting.

Journal of X-ray science and technology·2026

Same journal

Attention based multi-scale edge-aware segmentation and convolutional transformer framework for automated glaucoma detection from fundus images.

Journal of X-ray science and technology·2026

Same journal

Improving the robustness of radiomic features to patient size variations in CBCT imaging for radiotherapy.

Journal of X-ray science and technology·2026

Same journal

DH-OOD: A decoupled hybrid framework for robust skin lesion classification via semantic-structural fusion.

Journal of X-ray science and technology·2026

Same journal

Development and evaluation of deep learning models for automatic coronary stenosis segmentation in X-ray angiography.

Journal of X-ray science and technology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 12, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

A few-shot segmentation method for prohibited item inspection.

Zhenyue Zhu¹, Shujing Lyu¹, Yue Lu¹

¹Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China.

Journal of X-Ray Science and Technology

|March 22, 2021

Summary

This summary is machine-generated.

This study introduces an Attention-Based Graph Matching Network for effective prohibited item detection using few-shot learning. The model accurately segments items even with limited data and new categories, outperforming existing methods.

Keywords:

X-ray images few-shot semantic segmentation graph attention mechanism prohibited item inspection

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry

Published on: April 29, 2020

Related Experiment Videos

Last Updated: Nov 12, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry

Published on: April 29, 2020

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Deep learning models for prohibited item segmentation require extensive labeled data.
Rarely appearing items and evolving categories pose challenges for traditional methods.
Existing approaches struggle with limited annotated samples and new item types.

Purpose of the Study:

To develop a few-shot semantic segmentation network for prohibited item inspection.
To enable prediction of prohibited items with minimal annotated samples.
To inspect new categories of prohibited items without retraining.

Main Methods:

An Attention-Based Graph Matching Network is proposed.
Graph modeling between query and support images.
Graph Attention Units with similarity and equal weights for attentive matching.

Main Results:

The proposed model outperforms state-of-the-art models on Xray-PI and SIXray datasets.
Demonstrated superior performance in few-shot learning scenarios for prohibited item segmentation.
Achieved higher accuracy in segmenting prohibited items from X-ray images.

Conclusions:

The similarity loss function and space restriction module enhance segmentation accuracy.
The model effectively handles noise and supplements spatial information for better prohibited item detection.
This approach offers a robust solution for real-world security screening challenges.