论文标题
频繁的原型关系，用于几次分段
Interclass Prototype Relation for Few-Shot Segmentation
论文作者
论文摘要
传统的语义细分需要大型标记的图像数据集，并且只能在预定义的类中预测。为了解决这个问题，很少有几个射击分段，只需要少数新目标类别的注释。但是，由于很少的分割，特征空间中的目标类数据分布稀疏，覆盖率较低，因为样本数据的略有变化。设置正确将目标类别与其他类别分开的分类边界是不可能的任务。特别是，很难对与边界附近目标类相似的类进行分类。这项研究提出了阶级原型关系网络（IPRNET），该网络通过降低其他类别之间的相似性来改善分离性能。我们对Pascal-5i和Coco-20i进行了广泛的实验，并表明IPRNET与先前的研究相比提供了最佳的分割性能。
Traditional semantic segmentation requires a large labeled image dataset and can only be predicted within predefined classes. To solve this problem, few-shot segmentation, which requires only a handful of annotations for the new target class, is important. However, with few-shot segmentation, the target class data distribution in the feature space is sparse and has low coverage because of the slight variations in the sample data. Setting the classification boundary that properly separates the target class from other classes is an impossible task. In particular, it is difficult to classify classes that are similar to the target class near the boundary. This study proposes the Interclass Prototype Relation Network (IPRNet), which improves the separation performance by reducing the similarity between other classes. We conducted extensive experiments with Pascal-5i and COCO-20i and showed that IPRNet provides the best segmentation performance compared with previous research.
