Prototype-Based Two-Stage Few-Shot Instance Segmentation with Flexible Novel Class Adaptation

Few-shot instance segmentation (FSIS) is devised to address the intricate challenge of instance segmentation when labeled data for novel classes is scant. Nevertheless, existing methodologies encounter notable constraints in the agile expansion of novel classes and the management of memory overhead....

ver descrição completa

Detalhes bibliográficos

Principais autores:	Qinying Zhu, Yilin Zhang, Peng Xiao, Mengxi Ying, Lei Zhu, Chengyuan Zhang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-09-01
coleção:	Mathematics
Assuntos:	few-shot instance segmentation incremental learning embedding representation memory optimization
Acesso em linha:	https://www.mdpi.com/2227-7390/13/17/2889
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!