Zobrazit v EDS

Efficient Multiclass Classification of Small Datasets Using a Novel Contrast Based Learning Approach

Uloženo v:
Podrobná bibliografie
Název: Efficient Multiclass Classification of Small Datasets Using a Novel Contrast Based Learning Approach
Autoři: Salma Fayaz, Syed Zubair Ahmad Shah, Assif Assad
Zdroj: Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering). 18:1678-1695
Informace o vydavateli: Bentham Science Publishers Ltd., 2025.
Rok vydání: 2025
Témata: 0211 other engineering and technologies, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology
Popis: Introduction: Deep learning models often face challenges in achieving optimal accuracy when classifying multiclass datasets, particularly when the dataset size is limited. This study introduces Contrast Based Learning (CBL), a novel data augmentation technique designed to address data scarcity. Methods: CBL innovatively concatenates multiple image and contrast learning to generate enriched datasets that exhibit a higher diversity of complex features. By focusing on the contrasts between various images, this method enhances the model's ability to learn nuanced features, thereby improving generalization and reducing overfitting. Results: Unlike traditional data augmentation methods, which rely on basic transformations, CBL dynamically concatenates images from different classes, creating complex inputs that provide the model with a more comprehensive training dataset. Experimental results show that CBL significantly improves classification accuracy and outperforms state-of-the-art methods across multiple small-scale multiclass datasets. Conclusion: The findings highlight the robustness of CBL in addressing data limitations, demonstrating its potential to advance the classification performance of deep learning models.
Druh dokumentu: Article
Jazyk: English
ISSN: 2352-0965
DOI: 10.2174/0123520965298906241023110601
Přístupové číslo: edsair.doi...........bf1e40eaa123169fa47e683a702019c2
Databáze: OpenAIRE
Popis
Abstrakt:Introduction: Deep learning models often face challenges in achieving optimal accuracy when classifying multiclass datasets, particularly when the dataset size is limited. This study introduces Contrast Based Learning (CBL), a novel data augmentation technique designed to address data scarcity. Methods: CBL innovatively concatenates multiple image and contrast learning to generate enriched datasets that exhibit a higher diversity of complex features. By focusing on the contrasts between various images, this method enhances the model's ability to learn nuanced features, thereby improving generalization and reducing overfitting. Results: Unlike traditional data augmentation methods, which rely on basic transformations, CBL dynamically concatenates images from different classes, creating complex inputs that provide the model with a more comprehensive training dataset. Experimental results show that CBL significantly improves classification accuracy and outperforms state-of-the-art methods across multiple small-scale multiclass datasets. Conclusion: The findings highlight the robustness of CBL in addressing data limitations, demonstrating its potential to advance the classification performance of deep learning models.
ISSN:23520965
DOI:10.2174/0123520965298906241023110601