Guardado en:
Detalles Bibliográficos
Autores principales: Farooq, Muhammad Ali, Yao, Wang, Schukat, Michael, Little, Mark A, Corcoran, Peter
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.05159
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929677564641280
author Farooq, Muhammad Ali
Yao, Wang
Schukat, Michael
Little, Mark A
Corcoran, Peter
author_facet Farooq, Muhammad Ali
Yao, Wang
Schukat, Michael
Little, Mark A
Corcoran, Peter
contents This study explores the utilization of Dermatoscopic synthetic data generated through stable diffusion models as a strategy for enhancing the robustness of machine learning model training. Synthetic data generation plays a pivotal role in mitigating challenges associated with limited labeled datasets, thereby facilitating more effective model training. In this context, we aim to incorporate enhanced data transformation techniques by extending the recent success of few-shot learning and a small amount of data representation in text-to-image latent diffusion models. The optimally tuned model is further used for rendering high-quality skin lesion synthetic data with diverse and realistic characteristics, providing a valuable supplement and diversity to the existing training data. We investigate the impact of incorporating newly generated synthetic data into the training pipeline of state-of-art machine learning models, assessing its effectiveness in enhancing model performance and generalization to unseen real-world data. Our experimental results demonstrate the efficacy of the synthetic data generated through stable diffusion models helps in improving the robustness and adaptability of end-to-end CNN and vision transformer models on two different real-world skin lesion datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05159
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
Farooq, Muhammad Ali
Yao, Wang
Schukat, Michael
Little, Mark A
Corcoran, Peter
Computer Vision and Pattern Recognition
Artificial Intelligence
This study explores the utilization of Dermatoscopic synthetic data generated through stable diffusion models as a strategy for enhancing the robustness of machine learning model training. Synthetic data generation plays a pivotal role in mitigating challenges associated with limited labeled datasets, thereby facilitating more effective model training. In this context, we aim to incorporate enhanced data transformation techniques by extending the recent success of few-shot learning and a small amount of data representation in text-to-image latent diffusion models. The optimally tuned model is further used for rendering high-quality skin lesion synthetic data with diverse and realistic characteristics, providing a valuable supplement and diversity to the existing training data. We investigate the impact of incorporating newly generated synthetic data into the training pipeline of state-of-art machine learning models, assessing its effectiveness in enhancing model performance and generalization to unseen real-world data. Our experimental results demonstrate the efficacy of the synthetic data generated through stable diffusion models helps in improving the robustness and adaptability of end-to-end CNN and vision transformer models on two different real-world skin lesion datasets.
title Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.05159