论文标题
数字图像识别使用单一的全部深网分类器的合奏
Digit Image Recognition Using an Ensemble of One-Versus-All Deep Network Classifiers
论文作者
论文摘要
在多类深网分类器中，单个分类器将不同类别的样本进行分类的负担。结果，未获得最佳分类精度。同样，由于在单个CPU/GPU上进行了CNN培训，培训时间也很长。但是，众所周知，使用分类器的集合会提高性能。同样，可以通过在单独的处理器上运行合奏的每个成员来减少培训时间。过去，合奏学习在不同程度上用于传统方法，这是一个热门话题。随着深度学习的出现，合奏学习也已应用于前者。但是，一个未开发并且具有潜力的领域是全部（OVA）深度集合学习。在本文中，我们探讨了它，并表明，通过使用深网的OVA集合，可以获得深层网络性能的改进。如本文所示，通过使用二进制分类（OVA）深网的集合，可以进一步提高深网的分类能力。我们针对数字图像识别和测试并在同一情况下对其进行测试并对其进行了测试。在拟议的方法中，单个OVA深网分类器专用于每个类别。随后，已经研究了OVA深网的集合。使用动量算法（SGDMA）的随机梯度下降（SGDMA），通过OVA训练技术对合奏中的每个网络进行了训练。对于测试样本的分类，将样本显示给集合中的每个网络。在预测得分投票之后，假定分数最大的网络已将样本分类。该实验已在MNIST数字数据集，USPS+ Digit数据集和MATLAB数字图像数据集上进行。我们提出的技术在所有数据集的数字图像识别上都优于基线。
In multiclass deep network classifiers, the burden of classifying samples of different classes is put on a single classifier. As the result the optimum classification accuracy is not obtained. Also training times are large due to running the CNN training on single CPU/GPU. However it is known that using ensembles of classifiers increases the performance. Also, the training times can be reduced by running each member of the ensemble on a separate processor. Ensemble learning has been used in the past for traditional methods to a varying extent and is a hot topic. With the advent of deep learning, ensemble learning has been applied to the former as well. However, an area which is unexplored and has potential is One-Versus-All (OVA) deep ensemble learning. In this paper we explore it and show that by using OVA ensembles of deep networks, improvements in performance of deep networks can be obtained. As shown in this paper, the classification capability of deep networks can be further increased by using an ensemble of binary classification (OVA) deep networks. We implement a novel technique for the case of digit image recognition and test and evaluate it on the same. In the proposed approach, a single OVA deep network classifier is dedicated to each category. Subsequently, OVA deep network ensembles have been investigated. Every network in an ensemble has been trained by an OVA training technique using the Stochastic Gradient Descent with Momentum Algorithm (SGDMA). For classification of a test sample, the sample is presented to each network in the ensemble. After prediction score voting, the network with the largest score is assumed to have classified the sample. The experimentation has been done on the MNIST digit dataset, the USPS+ digit dataset, and MATLAB digit image dataset. Our proposed technique outperforms the baseline on digit image recognition for all datasets.
