Few-Shot Object Detection via Sample Processing
Few-shot object detection (FSOD) eliminates the dependence on tremendous instances with manual annotations in conventional object detection. We deem that the scarcity of positive samples is the main reason that restricts the performance of FSOD detectors. In this paper, a novel FSOD model via sample...
Guardado en:
Autores principales: | Honghui Xu, Xinqing Wang, Faming Shao, Baoguo Duan, Peng Zhang |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/73554ba2e8104e98bad6e1cc5b4a79f8 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Automated Muzzle Detection and Biometric Identification via Few-Shot Deep Transfer Learning of Mixed Breed Cattle
por: Ali Shojaeipour, et al.
Publicado: (2021) -
Meta-Seg: A Generalized Meta-Learning Framework for Multi-Class Few-Shot Semantic Segmentation
por: Zhiying Cao, et al.
Publicado: (2019) -
Task-Aware Dual Prototypical Network for Few-Shot Human-Object Interaction Recognition
por: AN Ping, JI Zhong, LIU Xiyao
Publicado: (2021) -
Optimizing Few-Shot Learning Based on Variational Autoencoders
por: Ruoqi Wei, et al.
Publicado: (2021) -
Task-Adaptive Embedding Learning with Dynamic Kernel Fusion for Few-Shot Remote Sensing Scene Classification
por: Pei Zhang, et al.
Publicado: (2021)