Recently, graph neural networks (GNNs) have shown powerful ability to handle few-shot classification problem, which aims at classifying unseen samples when trained with limited labeled samples per class. GNN-based few-shot learning architectures mostly replace traditional metric with a learnable GNN. In the GNN, the nodes are set as the samples embedding, and the relationship between two connected nodes can be obtained by a network, the input of which is the difference of their embedding features. We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks. That is, this method of measuring relation does not take the task-level information into account. To this end, we propose a new relation measure method, namely the attention-based task-level relation module (ATRM), to explicitly model the task-level relation of one sample to all the others. The proposed module captures the relation representations between nodes by considering the sample-to-task instead of sample-to-sample embedding features. We conducted extensive experiments on four benchmark datasets: mini-ImageNet, tiered-ImageNet, CUB-200-2011, and CIFAR-FS. Experimental results demonstrate that the proposed module is effective for GNN-based few-shot learning.
翻译:最近,平面神经网络(GNNs)显示出处理少量分类问题的强大能力,目的是在每类经过有限的标签样本培训时对未见样品进行分类,而每类有有限的标签样本进行分类。基于GNN的少发学习结构大多用可学习的GNN来取代传统度量。在GNN中,将节点设置为样品嵌入,两个连接节点之间的关系可以通过网络获得,其输入是其嵌入特征的差异。我们认为,这种衡量样品关系关系的方法只用样本到样本的模型,而忽视不同任务的特殊性。也就是说,这种衡量关系的方法没有考虑到任务一级的信息。为此,我们提出了一种新的关系计量方法,即基于关注的任务级关系模块(ATRM),以明确模拟一个样本与所有其他样本的任务级关系。拟议模块通过考虑样本到任务,而不是样本到样本到样本的嵌入特征,来反映各节点之间的关系。我们在四个基准数据集上进行了广泛的实验:MIS-INet,该模型展示了基于G-IFS-INet的G-IM-IM-IM-IM-IM-IG-IM-IM-IM-IM-IM-IM-IM-IM-IM-IM-IM-IG-IG-IM-IM-IM-IM-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-A-I-I-I-I-D-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-