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...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Xingliang Zhu, Weiwei Yu, Xiaoyu Dong, Wei Zhang, Bin Kong
Format:	Artigo
Jezik:	Inglês
Izdano:	Elsevier 2025-11-01
Serija:	Alexandria Engineering Journal
Teme:	Universal image segmentation Masked transformer Refined masked attention
Online dostop:	http://www.sciencedirect.com/science/article/pii/S1110016825010361
Oznake:	Označite Brez oznak, prvi označite!