Prototypical network for Few shot learning tries to learn an embedding function in the encoder that embeds images with similar features close to one another in the embedding space. However, in this process, the support set samples for a task are embedded independently of one other, and hence, the inter-class closeness is not taken into account. Thus, in the presence of similar-looking classes in a task, the embeddings will tend to be close to each other in the embedding space and even possibly overlap in some regions, which is not desirable for classification. In this paper, we propose an approach that intuitively pushes the embeddings of each of the classes away from the others in the meta-testing phase, thereby grouping them closely based on the distinct class labels rather than only the similarity of spatial features. This is achieved by training the encoder network for classification using the support set samples and labels of the new task. Extensive experiments conducted on benchmark data sets show improvements in meta-testing accuracy when compared with Prototypical Networks and also other standard few-shot learning models.
翻译:少许拍摄学习的原型网络试图在编码器中学习一个嵌入功能,在嵌入空间中嵌入相近的图像。 但是,在这个过程中,任务支持集样本是独立嵌入的,因此,没有考虑到不同类别之间的近距离。 因此,在任务中存在相似的外观类别的情况下,嵌入器往往在嵌入空间中彼此接近,甚至在某些区域可能重叠,这不适合分类。 在本文中,我们建议采取一种方法,在元测试阶段将每个班级的嵌入直接推离其他班级,从而根据不同的类标签,而不是仅仅根据空间特征的相似性,将它们紧密分组。通过培训编码器网络,使用新任务的支持集样本和标签进行分类,实现这一点。在基准数据集上进行的广泛实验表明,与Protogic 网络和其他标准的微小学习模型相比,元测试准确度有所提高。