Authors :
E Hukuimwe; C Mafirabadza; LNhapi
Volume/Issue :
Volume 8 - 2023, Issue 11 - November
Google Scholar :
http://tinyurl.com/bdz7juru
Scribd :
http://tinyurl.com/mpcahrs3
DOI :
https://doi.org/10.5281/zenodo.10361718
Abstract :
Glaucoma is a prevalent eye disease that can
lead to irreversible vision loss if not detected and treated
early. Image classification techniques that make use of
deep learning models have been showing promising
results in diagnosing glaucoma.Traditional deep learning
models often require large amounts of labeled data to
achieve optimal performance.This paper explores the
application of attention-based pretrained models for
binary classification tasks using small datasets. However,
in many real-world scenarios such as obtaining a
substantial labeled dataset can be challenging or costly
such as in rare diseses such as glaucoma.To address this
issue, attention mechanisms have emerged as a powerful
technique to enhance the performance of pretrained
models by focusing on relevant features and samples.
This paper investigates the effectiveness of attentionbased pretrained models in the context of small datasets
for binary classification tasks. Experimental results
demonstrate that attention mechanisms can significantly
improve the performance of pretrained models on
limited data, making them a valuable tool for practical
applications.
Keywords :
Glaucoma, Deep Learning, Convolutional Neural Networks, Pretrained Models, Attention Mechanisms, Image Classification.
Glaucoma is a prevalent eye disease that can
lead to irreversible vision loss if not detected and treated
early. Image classification techniques that make use of
deep learning models have been showing promising
results in diagnosing glaucoma.Traditional deep learning
models often require large amounts of labeled data to
achieve optimal performance.This paper explores the
application of attention-based pretrained models for
binary classification tasks using small datasets. However,
in many real-world scenarios such as obtaining a
substantial labeled dataset can be challenging or costly
such as in rare diseses such as glaucoma.To address this
issue, attention mechanisms have emerged as a powerful
technique to enhance the performance of pretrained
models by focusing on relevant features and samples.
This paper investigates the effectiveness of attentionbased pretrained models in the context of small datasets
for binary classification tasks. Experimental results
demonstrate that attention mechanisms can significantly
improve the performance of pretrained models on
limited data, making them a valuable tool for practical
applications.
Keywords :
Glaucoma, Deep Learning, Convolutional Neural Networks, Pretrained Models, Attention Mechanisms, Image Classification.
