MR-Former: Improving universal image segmentation via refined masked-attention transformer

Mask-based universal image segmentation architectures, which focus attention within the mask region, have significantly enhanced both segmentation accuracy and speed, becoming a key component of universal image segmentation frameworks. However, existing methods often generate masks from the predicte...

Descripción completa

Detalles Bibliográficos

Autores principales:	Xingliang Zhu, Weiwei Yu, Xiaoyu Dong, Wei Zhang, Bin Kong
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	Elsevier 2025-11-01
Colección:	Alexandria Engineering Journal
Materias:	Universal image segmentation Masked transformer Refined masked attention
Acceso en línea:	http://www.sciencedirect.com/science/article/pii/S1110016825010361
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!