Paper Type
Complete
Abstract
Lightweight CNN architectures, known for their efficiency and speed without compromising accuracy, play a crucial role in addressing the challenges posed by limited training data availability and high computational resource demands. These architectures seamlessly integrate with transfer learning, a pivotal technique in deep learning that allows pre-trained models to be adapted for new tasks. Our study focused on evaluating a multi-stage transfer learning approach across various dataset sizes and truncated versions of the MobileNetV2 architecture for medical image classification. The results reveal that simpler models can perform competitively, whereas more complex models generally deliver higher accuracy. Furthermore, the significance of model complexity on target performance tends to diminish with smaller datasets.
Paper Number
1882
Recommended Citation
Godasu, Rajesh; Zeng, David; and Sutrave, Kruttika, "IMPACT OF DATASET SIZE AND TRANSFER LEARNING ON TRUNCATED LIGHTWEIGHT ARCHITECTURE" (2024). AMCIS 2024 Proceedings. 27.
https://aisel.aisnet.org/amcis2024/health_it/health_it/27
IMPACT OF DATASET SIZE AND TRANSFER LEARNING ON TRUNCATED LIGHTWEIGHT ARCHITECTURE
Lightweight CNN architectures, known for their efficiency and speed without compromising accuracy, play a crucial role in addressing the challenges posed by limited training data availability and high computational resource demands. These architectures seamlessly integrate with transfer learning, a pivotal technique in deep learning that allows pre-trained models to be adapted for new tasks. Our study focused on evaluating a multi-stage transfer learning approach across various dataset sizes and truncated versions of the MobileNetV2 architecture for medical image classification. The results reveal that simpler models can perform competitively, whereas more complex models generally deliver higher accuracy. Furthermore, the significance of model complexity on target performance tends to diminish with smaller datasets.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIGHEALTH