On filling the intra-class and inter-class gaps for few-shot segmentation

Yuxuan Zhang, Shuchang Wang, Zhenbo Shi, Wei Yang

Abstract: Highlights•This paper is extented by our conference paper in IJ- CAI’23 with 50% new content.•We propose FGNet for FSS to fill intra-class and inter- class gaps.•A novel Feature Transformation Module is proposed for feature enhancement.•We extend FGNet to 3D FSS task, and propose a uniform framework called FGNet++.•We conduct extensive experiments to validate the efficacy of our approach.