Evaluating Model Performance with Hard-Swish Activation Function Adjustments
Abstract
In the field of pattern recognition, achieving high accuracy is essential. While training a model to recognize different complex images, it is vital to fine-tune the model to achieve the highest accuracy possible. One strategy for fine-tuning a model involves changing its activation function. Most pre-trained models use ReLU as their default activation function, but switching to a different activation function like Hard-Swish could be beneficial. This study evaluates the performance of models using ReLU, Swish and Hard-Swish activation functions across diverse image datasets. Our results show a 2.06% increase in accuracy for models on the CIFAR-10 dataset and a 0.30% increase in accuracy for models on the ATLAS dataset. Modifying the activation functions in architecture of pre-trained models lead to improved overall accuracy.
Keywords
Cite
@article{arxiv.2410.06879,
title = {Evaluating Model Performance with Hard-Swish Activation Function Adjustments},
author = {Sai Abhinav Pydimarry and Shekhar Madhav Khairnar and Sofia Garces Palacios and Ganesh Sankaranarayanan and Darian Hoagland and Dmitry Nepomnayshy and Huu Phong Nguyen},
journal= {arXiv preprint arXiv:2410.06879},
year = {2024}
}
Comments
2 pages