For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data. However, the semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification. To alleviate these issues, we propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet). To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class differences. Notably, during testing, the proposed unlabeled branch is excluded without extra unlabeled data and computation. Furthermore, we extend the inter-class variability between foreground and background by proposing a novel multi-level prototype generation and interaction module. The different-grained complementarity between global and local prototypes allows for better distinction between similar categories. The qualitative and quantitative performance of RiFeNet surpasses the state-of-the-art methods on PASCAL-5i and COCO benchmarks.

翻译：对于小样本语义分割，首要任务是从有限的标注数据中提取类别特定的固有信息。然而，先前方法存在的语义模糊性和类间相似性限制了像素级前景-背景分类的准确性。为解决这些问题，我们提出了相关固有特征增强网络（RiFeNet）。为了提升前景实例的语义一致性，我们提出了一种无标注分支作为高效的数据利用方法，使模型学会提取对类内差异具有鲁棒性的固有特征。值得注意的是，在测试阶段，所提出的无标注分支被移除，无需额外无标注数据或计算量。此外，我们通过提出一种新颖的多层级原型生成与交互模块，扩展了前景与背景之间的类间差异性。全局原型与局部原型之间不同粒度的互补性，有助于更好地区分相似类别。RiFeNet在PASCAL-5i和COCO基准上的定性与定量性能均超越了现有最优方法。