Fine-Grained Feature Refinement and Spatial Alignment for Few-Shot Object Detection With Minimal Data

Few-shot object detection (FSOD) aims to detect objects from novel classes with minimal annotated examples. While prevailing meta-learning approaches extract class prototypes from the support branch and integrate them into the query branch for prediction, they often suffer from insufficient interact...

Полное описание

Библиографические подробности

Главные авторы:	Zhengheng Zhang, Suolan Liu, Hongyuan Wang
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Access
Предметы:	Few-shot object detection meta-learning feature alignment attention mechanism extreme few-shot
Online-ссылка:	https://ieeexplore.ieee.org/document/11408809/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!