Recent studies reveal that the remarkable performance of Vision transformers (ViTs) benefits from large receptive fields. For this reason, the large convolutional kernel design becomes an ideal solution to make Convolutional Neural Networks (CNNs) great again. However, the typical large convolutional kernels turn out to be hardware-unfriendly operators, resulting in discount compatibility of various hardware platforms. Thus, it is unwise to simply enlarge the convolutional kernel size. In this paper, we reveal that small convolutional kernels and convolution operations can achieve the closing effects of large kernel sizes. Then, we propose a shift-wise operator that ensures the CNNs capture long-range dependencies with the help of the sparse mechanism, while remaining hardware-friendly. Experimental results show that our shift-wise operator significantly improves the accuracy of a regular CNN while markedly reducing computational requirements. On the ImageNet-1k, our shift-wise enhanced CNN model outperforms the state-of-the-art models. Code & models at https://github.com/lidc54/shift-wiseConv.

最近的研究发现，视觉变换器（ViTs）的出色性能得益于大的接受域。因此，大型卷积核设计成为了使卷积神经网络（CNNs）再次伟大的理想解决方案。然而，典型的大卷积核证明是不符合各种硬件平台的操作符，导致不兼容。因此，简单地扩大卷积核尺寸是不明智的。本文中，我们揭示了小卷积核和卷积操作可以实现与大卷积核尺寸相近的效果。然后，我们提出了一种能够在保持硬件友好性的同时通过稀疏机制，确保CNNs捕捉长距离依赖关系的位移式操作符。实验结果表明，我们的位移式操作符显著提高了常规CNN的准确性，同时大幅降低了计算要求。在ImageNet-1k上，我们增强的位移式CNN模型胜过了最先进的模型。代码和模型详见该网址。

Shift-ConvNets：小卷积核具有大核效应