Nikhila Thribhuvan, Sudheep Elayidom, , " Transfer Learning for Feature Dimensionality Reduction", The International Arab Journal of Information Technology (IAJIT) ,Volume 19, Number 05, pp. 115 - 121, September 2022, doi: 10.34028/iajit/19/5/3 .

Abstract: Transfer learning is a machine learning methodology by which a model developed for achieving a task is exploited for another related job. Many pre-trained image classification models trained on ImageNet are used for transfer learning. These pre-trained networks could also be used for classifying out of domain images by retraining them. This paper, along with the existing application for these pre-trained models, is also being exploited for feature dimensionality reduction. Many dimensionality reduction methods are available; the pre-trained image models will help us perform both image feature extraction and dimensionality reduction in a single go using the same network. The fine-tuning of the fully connected layers of the pre- trained network is done to extract the image features; along with this fine-tuning, some more tweaking is done on the fully connected layers of these models to reduce the image feature dimensionality. Here, VGG-16 and VGG-19 are the pre-trained models considered for feature vector generation and dimensionality reduction. An analysis of the efficiency of features generated by these pre-trained networks in classifying the out-of-domain images is done. Three different variants of VGG-16 and VGG-19 are analysed. All the three variants developed gave an AUC value above 0.8, which is considered good.
URL: https://iajit.org/paper/391

@ARTICLE{391,
author={Nikhila Thribhuvan, Sudheep Elayidom, },
journal={The International Arab Journal of Information Technology (IAJIT)},
title={Transfer Learning for Feature Dimensionality Reduction},
volume={19},
number={05},
pages={115 - 121},
doi={10.34028/iajit/19/5/3 },
year={1970}

,abstract={Transfer learning is a machine learning methodology by which a model developed for achieving a task is exploited for another related job. Many pre-trained image classification models trained on ImageNet are used for transfer learning. These pre-trained networks could also be used for classifying out of domain images by retraining them. This paper, along with the existing application for these pre-trained models, is also being exploited for feature dimensionality reduction. Many dimensionality reduction methods are available; the pre-trained image models will help us perform both image feature extraction and dimensionality reduction in a single go using the same network. The fine-tuning of the fully connected layers of the pre- trained network is done to extract the image features; along with this fine-tuning, some more tweaking is done on the fully connected layers of these models to reduce the image feature dimensionality. Here, VGG-16 and VGG-19 are the pre-trained models considered for feature vector generation and dimensionality reduction. An analysis of the efficiency of features generated by these pre-trained networks in classifying the out-of-domain images is done. Three different variants of VGG-16 and VGG-19 are analysed. All the three variants developed gave an AUC value above 0.8, which is considered good.},
keywords={Dimensionality reduction, fine-tuning, transfer learning, VGG-16, VGG-19},
ISSN={2413-9351},
month={Jan}}

TY - JOUR
TI - Transfer Learning for Feature Dimensionality Reduction
T2 -
SP - 115
EP - 121
AU - Nikhila Thribhuvan
AU - Sudheep Elayidom
AU -
DO - 10.34028/iajit/19/5/3
JO - The International Arab Journal of Information Technology (IAJIT)
IS - 9
SN - 2413-9351
VO - 19
VL - 19
JA -
Y1 - Jan 1970
ER -
PY - 1970

AB - Transfer learning is a machine learning methodology by which a model developed for achieving a task is exploited for another related job. Many pre-trained image classification models trained on ImageNet are used for transfer learning. These pre-trained networks could also be used for classifying out of domain images by retraining them. This paper, along with the existing application for these pre-trained models, is also being exploited for feature dimensionality reduction. Many dimensionality reduction methods are available; the pre-trained image models will help us perform both image feature extraction and dimensionality reduction in a single go using the same network. The fine-tuning of the fully connected layers of the pre- trained network is done to extract the image features; along with this fine-tuning, some more tweaking is done on the fully connected layers of these models to reduce the image feature dimensionality. Here, VGG-16 and VGG-19 are the pre-trained models considered for feature vector generation and dimensionality reduction. An analysis of the efficiency of features generated by these pre-trained networks in classifying the out-of-domain images is done. Three different variants of VGG-16 and VGG-19 are analysed. All the three variants developed gave an AUC value above 0.8, which is considered good.