Transductive meta-learning with enhanced feature ensemble for few-shot semantic segmentation
Abstract This paper addresses few-shot semantic segmentation and proposes a novel transductive end-to-end method that overcomes three key problems affecting performance. First, we present a novel ensemble of visual features learned from pretrained classification and semantic segmentation networks wi...
Main Authors: | Amin Karimi, Charalambos Poullis |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-02-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-54640-6 |
Similar Items
-
Ensemble Transductive Propagation Network for Semi-Supervised Few-Shot Learning
by: Xueling Pan, et al.
Published: (2024-01-01) -
Dual Prototype Learning for Few Shot Semantic Segmentation
by: Wenxuan Li, et al.
Published: (2024-01-01) -
Distilling base-and-meta network with contrastive learning for few-shot semantic segmentation
by: Xinyue Chen, et al.
Published: (2023-11-01) -
Prototype as query for few shot semantic segmentation
by: Leilei Cao, et al.
Published: (2024-07-01) -
Meta-Seg: A Generalized Meta-Learning Framework for Multi-Class Few-Shot Semantic Segmentation
by: Zhiying Cao, et al.
Published: (2019-01-01)