.png){kind=icon}
Return
Task-aware meta-learner for few-shot segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2026.08.023.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Research Highlights • Task-aware meta-learning captures support-query correlations for unseen classes.
• Dynamic affinity modeling enables adaptive multi-scale target information transfer.
• Dynamic attention adapts to class-specific variations for accurate localization.
• Adaptive representations improve segmentation generalization to unseen categories.
• Delivers state-of-the-art performance on PASCAL-5i and COCO-20i efficiently.
Keywords:
Few-shot segmentation
Meta-learning
Semantic segmentation,
Journal
IF:
3.3
Papers:
8.0K
Citations:
1.6W
Organization
Cited Papers
No cited papers available