Humans excel at learning and recognizing objects, swiftly adapting to new concepts with just a few samples. However, current studies in computer vision on few-shot learning have not yet achieved human performance in integrating prior knowledge during the learning process. Humans utilize a hierarchical structure of object categories based on past experiences to facilitate learning and classification. Therefore, we propose a method named n-Hierarchy SEmantic Guided Attention (nHi-SEGA) that acquires abstract superclasses. This allows the model to associate with and pay attention to different levels of objects utilizing semantics and visual features embedded in the class hierarchy (e.g., house finch-bird-animal, goldfish-fish-animal, rose-flower-plant), resembling human cognition. We constructed an nHi-Tree using WordNet and Glove tools and devised two methods to extract hierarchical semantic features, which were then fused with visual features to improve sample feature prototypes.

人类擅长学习和识别物体，只需几个样本就能迅速适应新概念。然而，目前计算机视觉中关于小样本学习的研究尚未达到人类在学习过程中整合先验知识的水平。人类利用基于过去经验的对象类别的层次结构来促进学习和分类。因此，我们提出了一种名为 n-Hierarchy SEmantic Guided Attention (nHi-SEGA) 的方法来获取抽象超类。这使得模型能够利用类层次结构中嵌入的语义和视觉特征（例如，家雀-鸟-动物、金鱼-鱼-动物、玫瑰-花-植物）来关联并关注不同级别的对象，类似于人类认识。我们使用 WordNet 和 Glove 工具构建了 nHi-Tree，并设计了两种方法来提取分层语义特征，然后将其与视觉特征融合以改进样本特征原型。