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

[Kinase-Glo luminescent kinase assay for in vitro determination of PKA activity].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2012
Same author

Functional characterization of an arrestin gene on insecticide resistance of Culex pipiens pallens.

Parasites & vectors·2012
Same author

MiR-23a inhibits myogenic differentiation through down regulation of fast myosin heavy chain isoforms.

Experimental cell research·2012
Same author

Let-7b inhibits human cancer phenotype by targeting cytochrome P450 epoxygenase 2J2.

PloS one·2012
Same author

Role of IKK/NF-κB signaling in extinction of conditioned place aversion memory in rats.

PloS one·2012
Same author

Inhibition of poly(ADP-ribose) polymerase attenuates acute kidney injury in sodium taurocholate-induced acute pancreatitis in rats.

Pancreas·2012

Related Experiment Video

Updated: Sep 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

661

Attention Guided Global Enhancement and Local Refinement Network for Semantic Segmentation.

Jiangyun Li, Sen Zha, Chen Chen

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 18, 2022
    PubMed
    Summary

    This study introduces the Attention guided Global enhancement and Local refinement Network (AGLN) for semantic segmentation. AGLN improves context aggregation and feature refinement, achieving state-of-the-art results on benchmark datasets.

    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

    536
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    3.0K

    Related Experiment Videos

    Last Updated: Sep 26, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    661
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    536
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    3.0K

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Image Segmentation

    Background:

    • Encoder-decoder architectures are common for semantic segmentation but face limitations in capturing global context and handling noisy low-level features.
    • Existing upsampling methods like interpolation and deconvolution have restricted receptive fields, hindering global context encoding.
    • Skip connections in encoder-decoder networks can introduce noise from early encoder layers due to insufficient semantic information.

    Purpose of the Study:

    • To address the limitations of standard encoder-decoder networks in semantic segmentation.
    • To enhance the network's ability to capture global context and refine feature representations.
    • To develop a novel network architecture that improves performance on challenging segmentation tasks.

    Main Methods:

    • Proposed a Global Enhancement Method to aggregate and distribute global information across decoder layers.
    • Developed a Local Refinement Module to refine noisy encoder features using decoder feature guidance.
    • Integrated these methods into a Context Fusion Block to create the Attention guided Global enhancement and Local refinement Network (AGLN).

    Main Results:

    • AGLN demonstrated superior performance on PASCAL Context, ADE20K, and PASCAL VOC 2012 datasets.
    • Achieved state-of-the-art mean Intersection over Union (mIOU) of 56.23% on the PASCAL Context dataset using a ResNet-101 backbone.
    • The proposed methods effectively addressed the challenges of limited global context and noisy feature fusion.

    Conclusions:

    • The AGLN architecture significantly improves semantic segmentation performance by enhancing global context aggregation and local feature refinement.
    • The novel Context Fusion Block, incorporating Global Enhancement and Local Refinement, is effective in overcoming limitations of traditional encoder-decoder models.
    • The approach offers a promising direction for developing more robust and accurate semantic segmentation models.