Group-On: Boosting One-Shot Segmentation with Supportive Query

arXiv:2404.11871v1 Announce Type: new
Abstract: One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class. This task is challenging because target objects in the support and query images can be largely different in appearance and pose (i.e., intra-class variation). Prior works suggested that incorporating more annotated support images in few-shot settings boosts performances but increases costs due to additional manual labeling. In this paper, we propose a novel approach for ONE-shot semantic …

abstract arxiv boosting class cs.cv image images objects prior query segment segmentation semantic support type variation