Polarized Attention Weak Supervised Semantic Segmentation Network

Polarized Attention Weak Supervised Semantic Segmentation Network

Currently, weakly supervised semantic segmentation methods based on image-level annotation often rely on pseudo pixel masks generated by seed regions. However, the growth of seed regions is stochastic, and in cases where targets are occluded or overlapped in the image without additional reference in...

Descripción completa

Detalles Bibliográficos
Autores principales: Min Dai, Donghang Wu, Yang Dawei
Formato: Artículo
Lenguaje:English
Publicado: IEEE 2024-01-01
Colección:IEEE Access
Materias:
Weakly supervised learning
semantic segmentation
semantic perception
boundary detection
Acceso en línea:https://ieeexplore.ieee.org/document/10489906/

Internet

https://ieeexplore.ieee.org/document/10489906/

Ejemplares similares