The recognition performance of convolutional neural networks has surpassed that of humans in many computer vision areas. However, there is a large number of parameter redundancy in deep neural networks, especially the weights of the convolutional kernels. In this work, we propose a simple Diagonal-kernel, in which a standard square kernel is replaced by a diagonal kernel and an anti-diagonal kernel. Diagonal-kernels with fewer parameters can have similar or larger local receptive fields than square kernels. The performance of the Diagonal-kernel is firstly evaluated on two benchmark image classification datasets, CIFAR, and ImageNet. The experimental results indicate that the Diagonal-kernel can effectively reduce parameters and computational cost while maintaining high accuracy. Furthermore, compared with Vector-kernel, Diagonal-kernel has larger local receptive fields and is more efficient. Then, we test the Diagonal-kernel for fine-grained image and imbalanced image dataset. The results show that Diagonal-kernel has larger accuracy loss for fine-grained than the coarse-grain image, but the loss is tolerable. The imbalanced data does not influence the performance of the Diagonal-kernel. The proposed Diagonal-kernel is mainly for traditional convolution but not for depthwise convolution because the number of weights for deep convolution is very small.

在许多计算机视觉领域中，卷积神经网络的识别性能已经超过了人类。但是，深度神经网络中存在大量参数冗余，尤其是卷积核的权重。在这项工作中，我们提出了一个简单的对角核，其中标准方核被对角核和反对角核所替代。与方形核相比，参数较少的对角核可以具有相似或更大的局部接收场。首先在两个基准图像分类数据集CIFAR和ImageNet上评估对角核的性能。实验结果表明，对角核可在保持高精度的同时有效地减少参数和计算量。此外，与Vector-kernel相比，对角核具有较大的局部接受域，并且效率更高。然后，我们测试对角核的细粒度图像和不平衡图像数据集。结果表明，对角核的精度损失比粗粒度图像大，但这种损失是可以容忍的。不平衡的数据不会影响对角核的性能。所提出的对角核主要用于传统卷积，但不适用于深度卷积，因为深度卷积的权数非常小。不平衡的数据不会影响对角核的性能。所提出的对角核主要用于传统卷积，但不适用于深度卷积，因为深度卷积的权数非常小。不平衡的数据不会影响对角核的性能。所提出的对角核主要用于传统卷积，但不适用于深度卷积，因为深度卷积的权数非常小。