Scale-Hybrid Group Distillation with Knowledge Disentangling for Continual Semantic Segmentation

Continual semantic segmentation (CSS) aims to learn new tasks sequentially and extract object(s) and stuff represented by pixel-level maps of new categories while preserving the original segmentation capabilities even when the old class data is absent. Current CSS methods typically preserve the capa...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Zichen, Zhang, Xiaoliang, Shi, Zhaofeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10537153/
https://www.ncbi.nlm.nih.gov/pubmed/37765877
http://dx.doi.org/10.3390/s23187820

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10537153/
https://www.ncbi.nlm.nih.gov/pubmed/37765877
http://dx.doi.org/10.3390/s23187820

Ejemplares similares