ESAMask: Real-Time Instance Segmentation Fused with Efficient Sparse Attention

Instance segmentation is a challenging task in computer vision, as it requires distinguishing objects and predicting dense areas. Currently, segmentation models based on complex designs and large parameters have achieved remarkable accuracy. However, from a practical standpoint, achieving a balance...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Qian, Chen, Lu, Shao, Mingwen, Liang, Hong, Ren, Jie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10385500/
https://www.ncbi.nlm.nih.gov/pubmed/37514740
http://dx.doi.org/10.3390/s23146446

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10385500/
https://www.ncbi.nlm.nih.gov/pubmed/37514740
http://dx.doi.org/10.3390/s23146446

Ejemplares similares