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

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Epidemiological characteristics of spinal cord injury in Northwest China: a single hospital-based study.

Journal of orthopaedic surgery and research·2020

Same author

An Eu(III)-functionalized Sr-based metal-organic framework for fluorometric determination of Cr(III) and Cr(VI) ions.

Mikrochimica acta·2020

Same author

Switchable solvent N, N, N', N'-tetraethyl-1, 3-propanediamine was dissociated into cationic surfactant to promote cell disruption and lipid extraction from wet microalgae for biodiesel production.

Bioresource technology·2020

Same author

Bakuchiol Attenuates Oxidative Stress and Neuron Damage by Regulating Trx1/TXNIP and the Phosphorylation of AMPK After Subarachnoid Hemorrhage in Mice.

Frontiers in pharmacology·2020

Same author

Alterations of local functional connectivity in lifespan: A resting-state fMRI study.

Brain and behavior·2020

Same author

EEG Functional Connectivity Underlying Emotional Valance and Arousal Using Minimum Spanning Trees.

Frontiers in neuroscience·2020

Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026

Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026

Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Denoised Non-Local Neural Network for Semantic Segmentation.

Qi Song, Jie Li, Hao Guo

IEEE Transactions on Neural Networks and Learning Systems

|April 6, 2023

Summary

This summary is machine-generated.

This study introduces a denoised non-local (NL) network to reduce noise in attention maps for semantic segmentation. The new model achieves state-of-the-art performance on benchmark datasets.

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Aug 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Non-local (NL) networks are crucial for semantic segmentation, calculating pixel pair relationships via attention maps.
Existing NL models suffer from noisy attention maps with interclass and intraclass inconsistencies, reducing accuracy and reliability.

Purpose of the Study:

To address attention noise in NL networks for semantic segmentation.
To improve the accuracy and reliability of NL-based semantic segmentation models.

Main Methods:

Proposes a denoised NL network featuring a global rectifying (GR) block and a local retention (LR) block.
GR block uses class-level predictions to identify pixels belonging to the same category, reducing interclass noise.
LR block incorporates local dependencies to refine attention maps and reduce intraclass noise.

Main Results:

The denoised NL network achieved state-of-the-art mean of classwise intersection over union (mIoU) of 83.5% on Cityscapes.
The model reached 46.69% mIoU on the ADE20K dataset without external training data.
Demonstrated superior performance on challenging semantic segmentation benchmarks.

Conclusions:

The proposed denoised NL network effectively eliminates attention noises, significantly enhancing semantic segmentation performance.
The GR and LR blocks successfully address interclass and intraclass inconsistencies, respectively.
This method offers a robust solution for accurate and reliable semantic segmentation using NL networks.