Abstract For performing multi-class classification, deep neural networks almost always employ a One-vs-All (OvA) classification scheme with as many output units as there are classes in a dataset. The problem of this approach is that each output unit requires a complex decision boundary to separate examples from one class from all other examples. In this paper, we propose a novel One-vs-One (OvO) classification scheme for deep neural networks that trains each output unit to distinguish between a specific pair of classes. This method increases the number of output units compared to the One-vs-All classification scheme but makes learning correct decision boundaries much easier. In addition to changing the neural network architecture, we changed the loss function, created a code matrix to transform the one-hot encoding to a new label encoding, and changed the method for classifying examples. To analyze the advantages of the proposed method, we compared the One-vs-One and One-vs-All classification methods on three plant recognition datasets (including a novel dataset that we created) and a dataset with images of different monkey species using two deep architectures. The two deep convolutional neural network (CNN) architectures, Inception-V3 and ResNet-50, are trained from scratch or pre-trained weights. The results show that the One-vs-One classification method outperforms the One-vs-All method on all four datasets when training the CNNs from scratch. However, when using the two classification schemes for fine-tuning pre-trained CNNs, the One-vs-All method leads to the best performances, which is presumably because the CNNs had been pre-trained using the One-vs-All scheme.

中文翻译：

---

深度神经网络的一对一分类

摘要 为了执行多类分类，深度神经网络几乎总是采用一对多 (OvA) 分类方案，其输出单元与数据集中的类一样多。这种方法的问题是每个输出单元都需要一个复杂的决策边界来将一个类中的示例与所有其他示例分开。在本文中，我们为深度神经网络提出了一种新颖的一对一 (OvO) 分类方案，该方案训练每个输出单元以区分特定的一对类别。与 One-vs-All 分类方案相比，此方法增加了输出单元的数量，但更容易学习正确的决策边界。除了改变神经网络架构之外，我们还改变了损失函数，创建了一个代码矩阵，将 one-hot 编码转换为新的标签编码，并改变了分类示例的方法。为了分析所提出方法的优势，我们在三个植物识别数据集（包括我们创建的一个新数据集）和一个具有不同猴子物种图像的数据集上比较了 One-vs-One 和 One-vs-All 分类方法，使用两个深层架构。两个深度卷积神经网络 (CNN) 架构 Inception-V3 和 ResNet-50 从头开始​​训练或预训练权重。结果表明，当从头开始训练 CNN 时，一对一分类方法在所有四个数据集上都优于一对一分类方法。然而，当使用两种分类方案对预训练的 CNN 进行微调时，One-vs-All 方法会导致最佳性能，这可能是因为 CNN 已经使​​用 One-vs-All 方案进行了预训练。