论文标题
正规化池
Regularized Pooling
论文作者
论文摘要
在卷积神经网络（CNN）中，合并操作起着重要作用，例如降低和变形补偿。通常，对于每个内核，Max Pooling是用于本地池的最广泛使用的操作。但是，变形在相邻内核上可能在空间上平滑。这意味着最大池太灵活，无法补偿实际变形。换句话说，其过度的灵活性风险抵消了类之间的基本空间差异。在本文中，我们提出了正则池，这使得池操作中的值选择方向可以在相邻内核上空间平滑，以便仅补偿实际变形。在手写角色图像和纹理图像上实验的结果表明，正则池不仅提高了识别精度，而且还可以加速学习的收敛性，而与常规的合并操作相比。
In convolutional neural networks (CNNs), pooling operations play important roles such as dimensionality reduction and deformation compensation. In general, max pooling, which is the most widely used operation for local pooling, is performed independently for each kernel. However, the deformation may be spatially smooth over the neighboring kernels. This means that max pooling is too flexible to compensate for actual deformations. In other words, its excessive flexibility risks canceling the essential spatial differences between classes. In this paper, we propose regularized pooling, which enables the value selection direction in the pooling operation to be spatially smooth across adjacent kernels so as to compensate only for actual deformations. The results of experiments on handwritten character images and texture images showed that regularized pooling not only improves recognition accuracy but also accelerates the convergence of learning compared with conventional pooling operations.
