Expandable-RCNN: toward high-efficiency incremental few-shot object detection

This study aims at addressing the challenging incremental few-shot object detection (iFSOD) problem toward online adaptive detection. iFSOD targets to learn novel categories in a sequential manner, and eventually, the detection is performed on all learned categories. Moreover, only a few training sa...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yiting Li, Sichao Tian, Haiyue Zhu, Yeying Jin, Keqing Wang, Jun Ma, Cheng Xiang, Prahlad Vadakkepat
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Frontiers Media S.A. 2024-04-01
coleção:	Frontiers in Artificial Intelligence
Assuntos:	object detection few-shot learning zero-shot learning incremental learning long-tailed recognition
Acesso em linha:	https://www.frontiersin.org/articles/10.3389/frai.2024.1377337/full
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!