论文标题
CNN中的合奏学习与完全连接的子网增强
Ensemble learning in CNN augmented with fully connected subnetworks
论文作者
论文摘要
卷积神经网络（CNN）在一般对象识别任务中表现出色。在本文中，我们提出了一个称为Ensnet的新模型，该模型由一个基本CNN和多个完全连接的子网（FCSN）组成。在此模型中，基本CNN中最后一个卷积层生成的特征映射集沿通道分为不相交的子集，并将这些子集分配给FCSN。每个FCSN都经过独立于其他的训练，因此它可以从分配给其的特征映射的子集中预测类标签。总体模型的产出取决于基本CNN和FCSN的多数投票。使用MNIST，Fashion-Mnist和CIFAR-10数据集的实验结果表明，所提出的方法进一步改善了CNN的性能。特别是，恩斯尼特（Ensnet）在MNIST上达到了0.16％的最新错误率。
Convolutional Neural Networks (CNNs) have shown remarkable performance in general object recognition tasks. In this paper, we propose a new model called EnsNet which is composed of one base CNN and multiple Fully Connected SubNetworks (FCSNs). In this model, the set of feature-maps generated by the last convolutional layer in the base CNN is divided along channels into disjoint subsets, and these subsets are assigned to the FCSNs. Each of the FCSNs is trained independent of others so that it can predict the class label from the subset of the feature-maps assigned to it. The output of the overall model is determined by majority vote of the base CNN and the FCSNs. Experimental results using the MNIST, Fashion-MNIST and CIFAR-10 datasets show that the proposed approach further improves the performance of CNNs. In particular, an EnsNet achieves a state-of-the-art error rate of 0.16% on MNIST.
