Evaluating Model Performance with Hard-Swish Activation Function Adjustments

RECPAD 2024 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 func...

Full description

Saved in:

Bibliographic Details
Main Authors:	Pydimarry, Sai Abhinav, Khairnar, Shekhar Madhav, Palacios, Sofia Garces, Sankaranarayanan, Ganesh, Hoagland, Darian, Nepomnayshy, Dmitry, Nguyen, Huu Phong
Format:	Journal Article
Language:	English
Published:	09-10-2024
Subjects:	Computer Science - Computer Vision and Pattern Recognition
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	RECPAD 2024 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.
DOI:	10.48550/arxiv.2410.06879