RepConv: A novel architecture for image scene classification on Intel scenes dataset
Soudy, Mohamed; Afify, Yasmine M.; Badr, Nagwa;
Abstract
Image understanding and scene classification are keystone tasks in computer vision. The
advancement of technology and the abundance of available datasets in the field of image
classification and recognition study provide plenty of attempts for advancement. In the scene
classification problem, transfer learning is commonly utilized as a branch of machine learning.
Despite existing machine learning models' superior performance in image interpretation and scene
classification, there are still challenges to overcome. The weights and current models aren't suitable
in most circumstances. Instead of using the weights of data-dependent models, in this work, a novel
machine learning model for the scene classification task is provided that converges rapidly. The
proposed model has been tested on the Intel scenes dataset for a comprehensive evaluation of our
model. The proposed model RepConv over-performed four existing benchmark models in a low
number of epochs and training parameters, and it achieved 93.55 ± 0.11, 75.54 ± 0.14 accuracies for
training and validation data respectively. Furthermore, re-categorization of the data set is performed
for a new classification problem that is not previously reported in the literature (natural scenes; real
scenes). The accuracy of the proposed model on the binary model was 98.08 ± 0.05 on training data
and 92.70 ± 0.08 on validation data which is not reported previously in any other publication.
advancement of technology and the abundance of available datasets in the field of image
classification and recognition study provide plenty of attempts for advancement. In the scene
classification problem, transfer learning is commonly utilized as a branch of machine learning.
Despite existing machine learning models' superior performance in image interpretation and scene
classification, there are still challenges to overcome. The weights and current models aren't suitable
in most circumstances. Instead of using the weights of data-dependent models, in this work, a novel
machine learning model for the scene classification task is provided that converges rapidly. The
proposed model has been tested on the Intel scenes dataset for a comprehensive evaluation of our
model. The proposed model RepConv over-performed four existing benchmark models in a low
number of epochs and training parameters, and it achieved 93.55 ± 0.11, 75.54 ± 0.14 accuracies for
training and validation data respectively. Furthermore, re-categorization of the data set is performed
for a new classification problem that is not previously reported in the literature (natural scenes; real
scenes). The accuracy of the proposed model on the binary model was 98.08 ± 0.05 on training data
and 92.70 ± 0.08 on validation data which is not reported previously in any other publication.
Other data
Title | RepConv: A novel architecture for image scene classification on Intel scenes dataset | Authors | Soudy, Mohamed; Afify, Yasmine M. ; Badr, Nagwa | Keywords | Image scene classification;Intel scene classification;Machine learning;Deep learning | Issue Date | 1-May-2022 | Journal | International Journal of Intelligent Computing and Information Sciences | Volume | 22 | Issue | 2 | Start page | 63 | End page | 73 | ISSN | 2535-1710 | DOI | 10.21608/ijicis.2022.118834.1163 |
Attached Files
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
RepConv A novel architecture for image scene classification on Intel scenes dataset.pdf | 771.46 kB | Adobe PDF | Request a copy |
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.