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

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...

Full description

Bibliographic Details
Main Authors: Yiting Li, Sichao Tian, Haiyue Zhu, Yeying Jin, Keqing Wang, Jun Ma, Cheng Xiang, Prahlad Vadakkepat
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-04-01
Series:Frontiers in Artificial Intelligence
Subjects:
object detection
few-shot learning
zero-shot learning
incremental learning
long-tailed recognition
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2024.1377337/full

Internet

https://www.frontiersin.org/articles/10.3389/frai.2024.1377337/full

Similar Items