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

Search research articles

Related Experiment Video

Updated: Oct 9, 2025

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

Comparison of Different Image Data Augmentation Approaches.

Loris Nanni¹, Michelangelo Paci², Sheryl Brahnam³

¹Department of Information Engineering, University of Padua, Via Gradenigo 6, 35131 Padova, Italy.

Journal of Imaging

|December 23, 2021

Summary

This summary is machine-generated.

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

Ensemble Deep Learning Models on Raw DNA Sequences for Viral Genome Identification in Human Samples.

Sensors (Basel, Switzerland)·2026

Same author

Matrix-based vector representations in neural networks for classifying molecular biology data.

Bioinformatics advances·2025

Same author

Entropy-Regularized Attention for Explainable Histological Classification with Convolutional and Hybrid Models.

Entropy (Basel, Switzerland)·2025

Same author

Advancing Precision: A Comprehensive Review of MRI Segmentation Datasets from BraTS Challenges (2012-2025).

Sensors (Basel, Switzerland)·2025

Same author

Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera Data.

Sensors (Basel, Switzerland)·2025

Same author

Postprocessing for Skin Detection.

Journal of imaging·2024

Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026

Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026

Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026

Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026

Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026

Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026

See all related articles

This study enhances image classification by using data augmentation techniques, including novel wavelet and Gabor transforms, to improve convolutional neural network (CNN) generalizability, achieving state-of-the-art results on diverse datasets.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Convolutional Neural Networks (CNNs) are widely used for image classification.
CNNs often struggle with small datasets, leading to overfitting and poor generalizability.
Data augmentation is a key technique to address these limitations by expanding training data.

Purpose of the Study:

To investigate the performance of various data augmentation methods for image classification.
To introduce and evaluate two novel augmentation techniques: discrete wavelet transform and constant-Q Gabor transform.
To demonstrate the effectiveness of data augmentation ensembles for improving CNN performance.

Main Methods:

Finetuning pretrained ResNet50 networks on over ten different data augmentation strategies.

Keywords:

convolutional neural networks data augmentation deep learning ensemble

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Related Experiment Videos

Last Updated: Oct 9, 2025

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

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Implementing and testing novel augmentation methods based on discrete wavelet transform and constant-Q Gabor transform.

Evaluating ensembles of augmented CNNs across four diverse benchmark datasets (virus, bark, portrait, LIGO glitches).

Main Results:

The proposed ensemble of augmented classifiers achieved state-of-the-art or comparable performance across all four diverse datasets.
Experiments confirmed the superiority of the investigated data augmentation approaches.
The best-performing ensemble demonstrated robust generalizability on varied image classification tasks.

Conclusions:

Varying data augmentation strategies is a feasible and effective method for building high-performing ensembles of classifiers.
Data augmentation, especially with novel transforms, significantly enhances CNN performance on small or diverse datasets.
This approach offers a practical solution for improving image classification accuracy and robustness.