Guardado en:
Detalles Bibliográficos
Autores principales: Harrison, Josie, Hollberg, Alexander, Yu, Yinan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2404.08557
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929312444186624
author Harrison, Josie
Hollberg, Alexander
Yu, Yinan
author_facet Harrison, Josie
Hollberg, Alexander
Yu, Yinan
contents Computer vision models trained on Google Street View images can create material cadastres. However, current approaches need manually annotated datasets that are difficult to obtain and often have class imbalance. To address these challenges, this paper fine-tuned a Swin Transformer model on a synthetic dataset generated with DALL-E and compared the performance to a similar manually annotated dataset. Although manual annotation remains the gold standard, the synthetic dataset performance demonstrates a reasonable alternative. The findings will ease annotation needed to develop material cadastres, offering architects insights into opportunities for material reuse, thus contributing to the reduction of demolition waste.
format Preprint
id arxiv_https___arxiv_org_abs_2404_08557
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
Harrison, Josie
Hollberg, Alexander
Yu, Yinan
Computer Vision and Pattern Recognition
Machine Learning
Computer vision models trained on Google Street View images can create material cadastres. However, current approaches need manually annotated datasets that are difficult to obtain and often have class imbalance. To address these challenges, this paper fine-tuned a Swin Transformer model on a synthetic dataset generated with DALL-E and compared the performance to a similar manually annotated dataset. Although manual annotation remains the gold standard, the synthetic dataset performance demonstrates a reasonable alternative. The findings will ease annotation needed to develop material cadastres, offering architects insights into opportunities for material reuse, thus contributing to the reduction of demolition waste.
title Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2404.08557