Domain-Incremental Learning Paradigm for scene understanding via Pseudo-Replay Generation

Scene understanding is a computer vision task that involves grasping the pixel-level distribution of objects. Unlike most research focuses on single-scene models, we consider a more versatile proposal: domain-incremental learning for scene understanding. This allows us to adapt well-studied single-s...

Descripció completa

Dades bibliogràfiques

Autors principals:	Zhifeng Xie, Rui Qiu, Qile He, Mengtian Li, Xin Tan
Format:	Artigo
Idioma:	Inglês
Publicat:	Elsevier 2025-09-01
Col·lecció:	Graphical Models
Matèries:	Scene understanding Domain-incremental learning Pseudo-replay generation
Accés en línia:	http://www.sciencedirect.com/science/article/pii/S1524070325000372
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!