Deep Learning Model with GA-based Visual Feature Selection and Context Integration

Ranju Mandal, Basim Azam, Brijesh Verma, Mengjie Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Deep learning models have been very successful in computer vision and image processing applications. Since its inception, Convolutional Neural Network (CNN)-based deep learning models have consistently outperformed other machine learning methods on many significant image processing benchmarks. Many top-performing methods for image segmentation are also based on deep CNN models. However, deep CNN models fail to integrate global and local context alongside visual features despite having complex multi-layer architectures. We propose a novel three-layered deep learning model that learns independently global and local contextual information alongside visual features, and visual feature selection based on a genetic algorithm. The novelty of the proposed model is that One-vs-All binary class-based learners are introduced to learn Genetic Algorithm (GA) optimized features in the visual layer, followed by the contextual layer that learns global and local contexts of an image, and finally the third layer integrates all the information optimally to obtain the final class label. Stanford Background and CamVid benchmark image parsing datasets were used for our model evaluation, and our model shows promising results. The empirical analysis reveals that optimized visual features with global and local contextual information play a significant role to improve accuracy and produce stable predictions comparable to state-of-the-art deep CNN models.

Original languageEnglish
Title of host publication2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages288-295
Number of pages8
ISBN (Electronic)9781728183923
DOIs
Publication statusPublished - 2021
Event2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Virtual, Krakow, Poland
Duration: 28 Jun 20211 Jul 2021

Publication series

Name2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings

Conference

Conference2021 IEEE Congress on Evolutionary Computation, CEC 2021
Country/TerritoryPoland
CityVirtual, Krakow
Period28/06/211/07/21

Keywords

  • Deep learning
  • Genetic algorithm
  • Image parsing
  • Scene understanding
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'Deep Learning Model with GA-based Visual Feature Selection and Context Integration'. Together they form a unique fingerprint.

Cite this