论文标题
修复了平滑卷积层，用于避免CNN中的棋盘伪影
Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
论文作者
论文摘要
在本文中，我们提出了一个具有平滑度的固定卷积层，不仅用于避免在卷积神经网络（CNN）中避免棋盘伪影，而且还可以增强CNN的性能，其中其过滤器内核的平滑度可以由参数控制。众所周知，许多CNN在这两个过程中都会生成棋盘伪影：向上采样层的前向传播和稳固的卷积层的向后传播。所提出的层可以完美地防止由卷积层或上采样层（包括转置卷积层）引起的棋盘伪影。在具有四个CNN的图像分类实验中：一个简单的CNN，VGG8，RESNET-18和RESNET-101，将固定层应用于这些CNN可提高所有CNN的分类性能。另外，固定层首次将固定层应用于生成对抗网络（GAN）。从图像产生结果中，证明了一个更平滑的固定卷积层，使我们能够提高用gan产生的图像的质量。
In this paper, we propose a fixed convolutional layer with an order of smoothness not only for avoiding checkerboard artifacts in convolutional neural networks (CNNs) but also for enhancing the performance of CNNs, where the smoothness of its filter kernel can be controlled by a parameter. It is well-known that a number of CNNs generate checkerboard artifacts in both of two process: forward-propagation of upsampling layers and backward-propagation of strided convolutional layers. The proposed layer can perfectly prevent checkerboard artifacts caused by strided convolutional layers or upsampling layers including transposed convolutional layers. In an image-classification experiment with four CNNs: a simple CNN, VGG8, ResNet-18, and ResNet-101, applying the fixed layers to these CNNs is shown to improve the classification performance of all CNNs. In addition, the fixed layer are applied to generative adversarial networks (GANs), for the first time. From image-generation results, a smoother fixed convolutional layer is demonstrated to enable us to improve the quality of images generated with GANs.
