A Graph Convolutional Network for Visual Categorization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F24%3A50021806" target="_blank" >RIV/62690094:18450/24:50021806 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-981-97-6489-1_19" target="_blank" >http://dx.doi.org/10.1007/978-981-97-6489-1_19</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-97-6489-1_19" target="_blank" >10.1007/978-981-97-6489-1_19</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Graph Convolutional Network for Visual Categorization

Popis výsledku v původním jazyce

The Convolutional Neural Networks (CNNs) have attained enhanced performance over conventional feature descriptors for image classification. Recently, Graph Convolutional Networks (GCNs) have also been witnessed in achieving improved performances for visual classification in various domains. A typical GCN is pertinent for propagating deep features using graph-based message passing methods. There are several domains such as the disease diagnosis of humans and plants where GCN could be explored for further performance enhancement. Thus, ample research attention is essential for solving different kinds of visual classification problems. In this direction, this work integrates the benefits of CNN and GCN for improving the feature representation by building a spatial relation using a GCN. In this work, a simple deep learning model is proposed that extracts the high-level deep features using a backbone CNN. Then, a GCN is applied for enhancing feature representation capabilities further for image classification. The proposed method has achieved improved performances on seven benchmark public datasets representing dance postures, hand shapes, agriculture, medical imaging, and aerial scene classification. The proposed method is developed using four different CNN backbones. Particularly, the proposed method based on ResNet-50 backbone has attained 89.98% accuracy on Dance-12, 90.34% accuracy on REST hand shape, 94.06% accuracy on Kvasir, and 75.89% accuracy on ISIC skin cancer, 91.73% accuracy on AID aerial scene classification, and 95.24% accuracy on PlantPathology datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Název v anglickém jazyce

A Graph Convolutional Network for Visual Categorization

Popis výsledku anglicky

The Convolutional Neural Networks (CNNs) have attained enhanced performance over conventional feature descriptors for image classification. Recently, Graph Convolutional Networks (GCNs) have also been witnessed in achieving improved performances for visual classification in various domains. A typical GCN is pertinent for propagating deep features using graph-based message passing methods. There are several domains such as the disease diagnosis of humans and plants where GCN could be explored for further performance enhancement. Thus, ample research attention is essential for solving different kinds of visual classification problems. In this direction, this work integrates the benefits of CNN and GCN for improving the feature representation by building a spatial relation using a GCN. In this work, a simple deep learning model is proposed that extracts the high-level deep features using a backbone CNN. Then, a GCN is applied for enhancing feature representation capabilities further for image classification. The proposed method has achieved improved performances on seven benchmark public datasets representing dance postures, hand shapes, agriculture, medical imaging, and aerial scene classification. The proposed method is developed using four different CNN backbones. Particularly, the proposed method based on ResNet-50 backbone has attained 89.98% accuracy on Dance-12, 90.34% accuracy on REST hand shape, 94.06% accuracy on Kvasir, and 75.89% accuracy on ISIC skin cancer, 91.73% accuracy on AID aerial scene classification, and 95.24% accuracy on PlantPathology datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Networks and Systems

ISBN

978-981-9764-88-4

ISSN

2367-3370

e-ISSN

—

Počet stran výsledku

14

Strana od-do

257-270

Název nakladatele

Springer Science and Business Media Deutschland GmbH

Místo vydání

Singapore

Místo konání akce

Aizawl

Datum konání akce

15. 12. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—