AI RESEARCH

Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation

arXiv CS.CV

ArXi:2603.05952v1 Announce Type: new Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision, yet remains challenged by structural misalignment and cross-view inconsistency under large appearance or viewpoint variations. This paper tackles these challenges by