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: Apr 26, 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

Structurally enhanced incremental neural learning for image classification with subgraph extraction.

Yu-Bin Yang1, Ya-Nan Li, Yang Gao

  • 1State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China.

International Journal of Neural Systems
|August 13, 2014
PubMed
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

[Exploring active components and targets of Gentiana straminea in treating rheumatoid arthritis based on serum pharmacochemistry and network pharmacology].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026
Same author

Hierarchically Biporous Wick Vapor Chamber With Micro/Nano Condenser for Exceeding 600 W/cm<sup>2</sup> Heat Dissipation.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Earliest centripetal flaking system in eastern Eurasia reveals human behavioral complexity in late Middle Pleistocene China.

Journal of human evolution·2026
Same author

Emodin Promoted Intestinal Secretion of GLP-1 and Limited Cognitive Deficits in Young Bilateral Ovariectomized Rats.

International journal of molecular sciences·2026
Same author

OTUD6B-mediated K48 deubiquitination of FXR1 forms a positive feedback loop activating MEK2/ERK signaling in colorectal cancer liver metastasis.

Cell death & disease·2026
Same author

HFIP-Promoted Regioselective Allylation of Tetrahydroquinolines (C6) and Indolines (C5) with Vinyl Benzoxazinanones.

The Journal of organic chemistry·2026
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A new method, visualization-induced self-organized incremental neural network (ViSOINN), enhances image classification by learning structural relationships between visual words. This approach improves accuracy and efficiency for large-scale image datasets.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Traditional Bag-of-Features (BoF) models for image classification often overlook the structural relationships among visual words.
  • Existing codebook learning methods can be inefficient, require large training sets, and may not preserve data structure effectively.

Purpose of the Study:

  • To propose a novel structurally enhanced incremental neural learning technique for discriminative codebook representation in image classification.
  • To develop an online codebook graph learning method that incorporates relationships among visual words.

Main Methods:

  • Introduced visualization-induced self-organized incremental neural network (ViSOINN) for structurally enhanced incremental learning.
  • Employed an adaptive and competitive learning mechanism to embed hidden structural information into a dynamically evolving graph representation.
Keywords:
Incremental neural learningcodebook graph learningcompetitive learningimage classificationself-organized neural network

Related Experiment Videos

Last Updated: Apr 26, 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
  • Image features are coded via sub-graph extraction using the learned codebook graph, followed by classification.

    • Main Results:

    • ViSOINN efficiently learns codebooks from small datasets, preserving high discriminative power by modeling visual word relationships.
    • The method automatically learns codebooks without a fixed size and enhances data structure preservation.
    • Achieved markedly improved performance and reduced computational cost on Caltech-101 and Caltech-256 datasets.

    Conclusions:

    • ViSOINN offers significant advantages over classical BoF-based codebook learning algorithms.
    • The proposed technique enhances image classification performance and is suitable for large-scale applications.
    • ViSOINN effectively learns discriminative codebook representations by leveraging structural information and incremental learning.