Square convolution is a default unit in convolutional neural networks as it fits well on the tensor computation for convolution operation, which usually has a fixed N x N receptive field (RF). However, what matters most to the network is the effective receptive field (ERF), which indicates the extent each pixel contributes to the output. ERF shows a Gaussian distribution and can not be modeled by simply sampling pixels with offsets. To simulate ERF, we propose a Gaussian Mask convolutional kernel (GMConv) in this work. Specifically, GMConv utilizes the Gaussian function to generate a concentric symmetry mask and put the mask over the kernel to refine the RF. Our GMConv can directly replace the standard convolutions in existing CNNs and can be easily trained end-to-end by standard backpropagation. Extensive experiments on multiple image classification benchmark datasets show that our method is comparable to, and outperforms in many cases, the standard convolution. For instance, using GMConv for AlexNet and ResNet-50, the top-1 accuracy on ImageNet classification is boosted by 0.98% and 0.85%, respectively.

翻译：方形卷积是卷积神经网络中的默认单元，因为它能很好地适应卷积操作的张量计算，通常具有固定的N×N感受野。然而，对网络而言更重要的是有效感受野，它表示每个像素对输出的贡献程度。有效感受野呈现高斯分布，无法通过简单的偏移采样像素来建模。为模拟有效感受野，本文提出了一种高斯掩膜卷积核。具体而言，GMConv利用高斯函数生成同心对称掩膜，并将该掩膜覆盖于卷积核之上以优化感受野。我们的GMConv可直接替代现有卷积神经网络中的标准卷积，并通过标准反向传播轻松实现端到端训练。在多个图像分类基准数据集上的大量实验表明，我们的方法与标准卷积性能相当，且在多数情况下优于后者。例如，在AlexNet和ResNet-50中使用GMConv，其在ImageNet分类上的top-1准确率分别提升了0.98%和0.85%。