ReMarNet：小样本图像分类的联合关系和间隔学习
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification
摘要：
尽管实现了最先进的性能，但深度学习方法通常在训练期间需要大量的标记数据，并且在样本量小时可能会遭受过拟合。为了确保深度网络在小样本下的良好泛化能力，学习区分特征至关重要。为此，已经提出了几个损失函数来鼓励大的类内紧凑性和类间可分性。在本文中，我们建议从一个新的角度，通过引入一种新的神经网络，称为边缘和边缘学习网络（ReMarNet），以提高区分能力的功能。我们的方法组装了两个不同主干的网络，以便学习在上述两种分类机制中表现出色的特征。具体而言，利用样本与类原型的相似性，利用关系网络学习支持分类的特征，同时利用具有交叉熵损失的全连接网络通过决策边界进行分类.四个图像数据集上的实验表明，我们的方法是有效的学习判别特征从一个小的标记样本集，并实现了竞争力的性能对国家的最先进的方法。代码可在https://github.com/liyunyu08/ReMarNet上获得。
英文摘要：
Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Codes are available at https://github.com/liyunyu08/ReMarNet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
