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 Experiment Video

Updated: May 5, 2026

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

1.3K

Implicit Neural Representation with Dead-Free Linear Unit for Remote Sensing Images.

Yi Lu1, Chang Lu2, Dongshen Han2

  • 1School of Mathematical Sciences, Capital Normal University, Beijing 100088, China.

Sensors (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

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

Investigation of optical properties of Ag nanoparticle aggregates for enhanced solar photothermal conversion.

Optics express·2025
Same author

HCDFI-YOLOv8: A Transmission Line Ice Cover Detection Model Based on Improved YOLOv8 in Complex Environmental Contexts.

Sensors (Basel, Switzerland)·2025
Same author

Robust Plasmonic Structures Fabricated by Femtosecond Laser-Assisted Anisotropic Intaglio Engraving on Quartz for High-Sensitivity Surface Plasmon Resonance Sensing.

ACS applied materials & interfaces·2025
Same author

Clinical significance of a novel inflammatory-nutritional index in glaucoma severity evaluation.

Biomolecules & biomedicine·2025
Same author

Maternal Physical Activity and Its Relationship to the Human Milk Metabolome and Infant Body Composition.

The Journal of clinical endocrinology and metabolism·2025
Same author

Carbon nanotube-wrapped particles in sodium alginate hydrogels for enhanced solar evaporation and EMI shielding through tortuous channel.

International journal of biological macromolecules·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces the Dead-Free Linear Unit (DeLU), a novel activation function for Implicit Neural Representations (INRs). DeLU improves image modeling in AI agents by eliminating dead regions in neural networks.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Implicit Neural Representations (INRs) are vital for multimodal sensing in AI agents.
  • Multi-Layer Perceptrons (MLPs) learn image representations by mapping coordinates to intensities.
  • The ReLU activation function's dead region limits INR expressiveness.

Purpose of the Study:

  • To address the limitations of the ReLU activation function in MLP-based INRs.
  • To introduce a novel activation function that enhances INR performance.
  • To improve the modeling of remote sensing images using INRs.

Main Methods:

  • Developed the Dead-Free Linear Unit (DeLU) activation function.
  • DeLU utilizes a linearly transformed absolute value to avoid inactive regions.
Keywords:
Implicit Neural Representationrectified linear unitremote sensing

More Related Videos

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

918

Related Experiment Videos

Last Updated: May 5, 2026

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

1.3K
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

918
  • Integrated DeLU with periodic activations and adaptive linear scaling in MLPs.

    • Main Results:

    • DeLU effectively eliminates inactive regions in activation functions.
    • The proposed DeLU enhances the expressiveness of INR architectures.
    • Experiments on diverse remote sensing datasets demonstrate DeLU's efficacy.

    Conclusions:

    • DeLU offers a significant improvement over traditional activation functions for INRs.
    • The novel activation function enhances the performance of AI agents in remote sensing tasks.
    • DeLU represents a promising advancement in neural representation for image modeling.