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

You might also read

Related Articles

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

Sort by

Same author

Quantifying the Waddington landscape and biological paths for development and differentiation.

Proceedings of the National Academy of Sciences of the United States of America·2011

Same author

[Evaluation on the effects of an education program regarding the sedentary behavior among school-aged children using Transtheoretical Model].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2011

Same author

[The application of near-infrared diffuse reflection spectra based on the principle of linear additive in tobacco redrying formula].

Guang pu xue yu guang pu fen xi = Guang pu·2011

Same author

Genetic study of families affected with aggressive periodontitis.

Periodontology 2000·2011

Same author

[Experimental study on Qi deficiency and blood stasis induced by muti-factor stimulation in rats].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2011

Same author

Improved visible light photocatalytic activity of sphere-like BiOBr hollow and porous structures synthesized via a reactable ionic liquid.

Dalton transactions (Cambridge, England : 2003)·2011

Same journal

DARUMA: a gateway to fast and easy prediction of intrinsically disordered regions.

PeerJ. Computer science·2026

Same journal

Alzheimer's disease detection using a quantum deep neural network with Haralick feature extraction and simulated annealing optimization.

PeerJ. Computer science·2026

Same journal

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network.

PeerJ. Computer science·2026

Same journal

An anomaly detection model for multivariate time series with anomaly perception.

PeerJ. Computer science·2026

Same journal

Retraction: A wormhole attack detection method for tactical wireless sensor networks.

PeerJ. Computer science·2026

Same journal

Evaluation of mental disorder with prioritization of its type by utilizing the bipolar complex fuzzy decision-making approach based on Schweizer-Sklar prioritized aggregation operators.

PeerJ. Computer science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 5, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Adaptive prototype few-shot image classification method based on feature pyramid.

Linshan Shen¹, Xiang Feng¹, Li Xu¹

¹College of Computer Science And Technology, Harbin Engineering University, Harbin, HeiLongJiang, China.

Peerj. Computer Science

|December 9, 2024

Summary

This summary is machine-generated.

This study introduces the Adaptive Prototype few-shot image classification method based on Feature Pyramid (APFP) to improve machine learning with limited data. APFP enhances feature extraction and dynamically computes class prototypes, achieving high accuracy on benchmark datasets.

Keywords:

Few-shot learning Image classification Metric learning Prototype network

More Related Videos

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

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Related Experiment Videos

Last Updated: Jun 5, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

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

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Few-shot learning (FSL) aims to classify novel classes with minimal data, mimicking human learning.
Metric learning is vital for FSL, relying on effective feature extraction and prototype computation.
Existing prototype methods struggle with diverse sample distributions in few-shot scenarios.

Purpose of the Study:

To introduce an Adaptive Prototype few-shot image classification method based on Feature Pyramid (APFP).
To enhance feature representation and address limitations in traditional prototype computation for FSL.

Main Methods:

Developed FResNet, a novel feature extractor based on ResNet with a feature pyramid for detailed information retention.
Proposed an Adaptive Prototype (AP) method that dynamically computes class prototypes using sample-query similarity.
Integrated FResNet and AP into the APFP framework for few-shot image classification.

Main Results:

APFP achieved 67.98% accuracy in 5-way 1-shot and 85.32% in 5-way 5-shot on MiniImageNet.
On the CUB dataset, APFP reached 84.02% accuracy in 5-way 1-shot and 94.44% in 5-way 5-shot.
Demonstrated superior performance compared to traditional methods, validating the effectiveness of APFP.

Conclusions:

The proposed APFP method effectively addresses the challenges of few-shot image classification.
Adaptive prototype computation and enhanced feature extraction are key to improving FSL performance.
APFP shows significant potential for real-world applications requiring rapid learning from limited examples.