Input Image Pixel Interval method for Classification Using Transfer Learning

Abdulaziz Anorboev, Musaev Javokhir, Jeongkyu Hong, Ngoc Thanh Nguyen, Dosam Hwang

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

1 Scopus citations

Abstract

Deep learning has been used in many applications where patterns from past-trained data can be extracted to predict future outcomes. Deep learning is characterized by training and testing data with the identical input feature space and same data distribution. However, whereas the data distribution is same between the training and testing data, the results might be different. This study introduces input image preprocessing, an enhanced neural network optimization method, and prediction probability ensemble to minimize the number of trainable parameters but maintain the outcome accuracy. In the suggested methodology, input images are separated into pixel interval and the fully connected layer jointly used with saved weights. Outcome results of separated input images are ensembled to the corresponding class probabilities of the original image. The results of the proposed method were compared with those of other previous methods in the image classification task and achieved successful performance accuracies in several datasets.

Original languageEnglish
Title of host publication16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022
EditorsRichard Chbeir, Tulay Yildirim, Ladjel Bellatreche, Yannis Manolopoulos, Apostolos Papadopoulos, Karam Bou Chaaya
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665498104
DOIs
StatePublished - 2022
Event16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022 - Biarritz, France
Duration: 8 Aug 202212 Aug 2022

Publication series

Name16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022

Conference

Conference16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022
Country/TerritoryFrance
CityBiarritz
Period8/08/2212/08/22

Keywords

  • classification probability
  • ensemble learning
  • model optimization

Fingerprint

Dive into the research topics of 'Input Image Pixel Interval method for Classification Using Transfer Learning'. Together they form a unique fingerprint.

Cite this