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

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by

Same author

Opportunities and challenges for the application of single-cell RNA sequencing and spatial transcriptomics in ischemic stroke.

Experimental neurology·2026

Same author

Stable lineages, rewired landscapes: single-cell and spatial multi-omics reveal developmental plasticity under abiotic stress.

The New phytologist·2026

Same author

Activatable fluorescent nanosensor for real-time detection and intracellular imaging of histone deacetylase 1.

Analytical and bioanalytical chemistry·2026

Same author

Si-Based Lithium-Ion Battery Anodes: Material Design and Challenges.

Materials (Basel, Switzerland)·2026

Same author

Comparative study of the post-helical crus approach for excision of classic preauricular sinuses.

International journal of pediatric otorhinolaryngology·2026

Same author

Unveiling the pathogenesis and therapeutic strategies of Alzheimer's disease through cuproptosis.

Biometals : an international journal on the role of metal ions in biology, biochemistry, and medicine·2026

Search research articles

Related Experiment Video

Updated: Sep 18, 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

Eternal-MAML: a meta-learning framework for cross-domain defect recognition.

Jipeng Feng^1,2, Haigang Zhang², Zhifeng Wang¹

¹School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, China.

Peerj. Computer Science

|June 26, 2025

Summary

Industrial defect recognition models struggle with limited data. Eternal-MAML improves cross-domain transfer learning by addressing label arrangement issues and enhancing feature extraction, outperforming existing methods.

Keywords:

Computer vision Industrial visual detection Model-agnostic meta-learning

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Sep 18, 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

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Computer Vision
Machine Learning
Industrial Quality Control

Background:

Deep learning models for industrial defect recognition face sample scarcity, limiting generalizability.
Transfer learning from natural image datasets often leads to overfitting in pixel-level defect recognition due to data scarcity.
Variations in defect characteristics across industrial products hinder direct model transfer, causing performance degradation.

Purpose of the Study:

To propose a novel Model-Agnostic Meta-Learning (MAML) framework, Eternal-MAML, to enhance cross-domain defect recognition.
To address label arrangement issues in MAML that negatively impact training and testing performance.
To improve model transfer accuracy and training stability for industrial defect recognition tasks with limited data.

Main Methods:

Developed Eternal-MAML, a novel MAML framework guiding classifier updates with a shared meta-vector in the inner loop.
Integrated Squeeze-and-Excitation modules and Residual blocks into the feature extractor for enhanced stability and generalization.
Validated the framework on multiple datasets using simulation experiments to assess cross-domain meta-learning performance.

Main Results:

The proposed Eternal-MAML framework demonstrated superior performance compared to state-of-the-art baselines in average normalized accuracy.
The framework effectively mitigates overfitting and improves knowledge transfer across different industrial defect recognition tasks.
Ablation studies confirmed the significant contribution of individual components to the overall performance enhancement.

Conclusions:

Eternal-MAML offers an effective solution for industrial defect recognition with limited samples by improving meta-learning strategies.
The framework enhances model generalizability and robustness for cross-domain defect classification tasks.
The proposed approach provides a promising direction for advancing automated quality inspection in industrial settings.