Revolutionizing Alloy Microstructure Segmentation through SAM and Domain Knowledge without Extra Training

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Xudong, Zhang, Yuqi, Wang, Chenchong, Xu, Wei
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910515860602880
author Ma, Xudong
Zhang, Yuqi
Wang, Chenchong
Xu, Wei
author_facet Ma, Xudong
Zhang, Yuqi
Wang, Chenchong
Xu, Wei
contents Fundamental models, trained on large-scale datasets and adapted to new data using innovative learning methods, have revolutionized various fields. In materials science, microstructure image segmentation plays a pivotal role in understanding alloy properties. However, conventional supervised modelling algorithms often necessitate extensive annotations and intricate optimization procedures. The segmentation anything model (SAM) introduces a fresh perspective. By combining SAM with domain knowledge, we propose a novel generalized algorithm for alloy image segmentation. This algorithm can process batches of images across diverse alloy systems without requiring training or annotations. Furthermore, it achieves segmentation accuracy comparable to that of supervised models and robustly handles complex phase distributions in various alloy images, regardless of data volume.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04922
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revolutionizing Alloy Microstructure Segmentation through SAM and Domain Knowledge without Extra Training
Ma, Xudong
Zhang, Yuqi
Wang, Chenchong
Xu, Wei
Materials Science
Fundamental models, trained on large-scale datasets and adapted to new data using innovative learning methods, have revolutionized various fields. In materials science, microstructure image segmentation plays a pivotal role in understanding alloy properties. However, conventional supervised modelling algorithms often necessitate extensive annotations and intricate optimization procedures. The segmentation anything model (SAM) introduces a fresh perspective. By combining SAM with domain knowledge, we propose a novel generalized algorithm for alloy image segmentation. This algorithm can process batches of images across diverse alloy systems without requiring training or annotations. Furthermore, it achieves segmentation accuracy comparable to that of supervised models and robustly handles complex phase distributions in various alloy images, regardless of data volume.
title Revolutionizing Alloy Microstructure Segmentation through SAM and Domain Knowledge without Extra Training
topic Materials Science
url https://arxiv.org/abs/2407.04922