Jove
Visualize
Contact Us

Related Experiment Videos

GNTF: A Lightweight CNN Robustness Enhancement Method for IoT Devices.

Xuan Liu1,2,3, Benkui Zhang1,2,4,5, Jinxiao Wang1,2

  • 1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China.

Sensors (Basel, Switzerland)
|April 14, 2026
PubMed
Summary

Related Concept Videos

Reducing Line Loss01:18

Reducing Line Loss

451
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
451

You might also read

Related Articles

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

Sort by
Same author

TWEAK Receptor Promotes Vascular Remodeling in Hypertension by Activating Autophagy.

Journal of the American Heart Association·2026
Same author

Abscisic acid confers antibiotic stress tolerance in cucumber by alleviating antibiotic phytotoxicity and decreasing the levels of antibiotic and antibiotic resistance genes.

Journal of hazardous materials·2026
Same author

Grafting Alleviates the Single and Combined Salt and Phytophthora capsici Stress in Tomato by Activating Salicylic Acid-Mediated Defence Pathway.

Physiologia plantarum·2025
Same author

High-performance electrochromic aqueous batteries enabled by Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub> anodes: Bridging Electrochromism and efficient energy storage.

Journal of colloid and interface science·2025
Same author

Comprehensive analysis of groundwater hydrochemistry and nitrate health risks in the Baiquan basin, Northern China.

PeerJ·2025
Same author

Nondestructive evaluation of yellowing and senescence in 'Yali' pear using integrated hyperspectral and chlorophyll fluorescence imaging.

Food research international (Ottawa, Ont.)·2025
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

This study introduces a Generative Nonlinear Transformation Filter (GNTF) to enhance lightweight convolutional neural networks (CNNs) for Internet of Things (IoT) devices. The GNTF improves performance on corrupted data by generating filters, boosting robustness and accuracy in challenging environments.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Internet of Things (IoT)

Background:

  • Lightweight convolutional neural networks (CNNs) are crucial for vision tasks on resource-constrained Internet of Things (IoT) devices.
  • Performance of these CNNs degrades significantly in outdoor environments due to corrupted data (e.g., fog, rain).

Purpose of the Study:

  • To propose a Generative Nonlinear Transformation Filter (GNTF) method to enhance the generalization performance of lightweight CNNs on corrupted data.
  • To improve the robustness and accuracy of CNNs deployed on IoT devices operating in adverse conditions.

Main Methods:

  • The GNTF method utilizes a subset of filters as learnable parameters (seed filters).
  • Remaining filters are generated via nonlinear transformation of seed filters, which are fixed during training.
Keywords:
IoT devicesMonoCNNedge computing

Related Experiment Videos

  • The method focuses on replacing depthwise convolutional modules and applying simple translation transformations.

    • Main Results:

    • The GNTF method demonstrated improved accuracy on corrupted datasets (CIFAR-10-C, CIFAR-100-C) across various lightweight CNN architectures.
    • Experiments showed enhanced robustness and generalization performance without significantly increasing trainable parameters.
    • For instance, ShuffleNetV2 with GNTF achieved a 3.3% accuracy improvement on CIFAR-10-C with fewer parameters.

    Conclusions:

    • The proposed GNTF method effectively enhances the performance of lightweight CNNs on degraded data.
    • This approach offers a viable solution for deploying reliable vision services on IoT devices in complex outdoor environments.
    • GNTF contributes to more robust and efficient AI on edge devices.