论文标题
自适应神经元的判别标准和隐藏层的自适应中心损失，用于深卷积神经网络
Adaptive Neuron-wise Discriminant Criterion and Adaptive Center Loss at Hidden Layer for Deep Convolutional Neural Network
论文作者
论文摘要
与其他技术相比，深层卷积神经网络（CNN）已被广泛用于图像分类，并具有更好的分类准确性。 SoftMax跨凝性损失函数通常用于分类任务。有一些工作可以在目标函数中引入其他术语以供训练，以使输出层的特征更具歧视性。神经元的判别标准通过将判别标准引入每个特征，从而使输出层判别中每个神经元的输入特征。同样，将中心的损失引入了软性激活函数之前的特征，以使面部识别以使深度特征具有歧视性。 RELU函数通常用于网络作为CNN隐藏层中的活动函数。但是，观察到，使用Relu函数训练的深度特征不够歧视并显示出细长的形状。在本文中，我们建议在输出层处使用神经元的判别标准，并在隐藏层处使用中心损失。另外，我们介绍了每堂课的在线计算，并以指数遗忘的方式介绍了。我们将他们命名为自适应神经元的判别标准和自适应中心损失。 MNSIT，FashionMnist，CIFAR10，CIFAR100和STL10的实验显示了自适应神经元判别标准和自适应中心损失的整合的有效性。源代码在https://github.com/i13abe/adaptive-discriminant-and-center上
A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classification tasks. There are some works to introduce the additional terms in the objective function for training to make the features of the output layer more discriminative. The neuron-wise discriminant criterion makes the input feature of each neuron in the output layer discriminative by introducing the discriminant criterion to each of the features. Similarly, the center loss was introduced to the features before the softmax activation function for face recognition to make the deep features discriminative. The ReLU function is often used for the network as an active function in the hidden layers of the CNN. However, it is observed that the deep features trained by using the ReLU function are not discriminative enough and show elongated shapes. In this paper, we propose to use the neuron-wise discriminant criterion at the output layer and the center-loss at the hidden layer. Also, we introduce the online computation of the means of each class with the exponential forgetting. We named them adaptive neuron-wise discriminant criterion and adaptive center loss, respectively. The effectiveness of the integration of the adaptive neuron-wise discriminant criterion and the adaptive center loss is shown by the experiments with MNSIT, FashionMNIST, CIFAR10, CIFAR100, and STL10. Source code is at https://github.com/i13abe/Adaptive-discriminant-and-center
