The square kernel is a standard unit for contemporary CNNs, as it fits well on the tensor computation for convolution operation. However, the retinal ganglion cells in the biological visual system have approximately concentric receptive fields. Motivated by this observation, we propose to use circular kernel with a concentric and isotropic receptive field as an option for the convolution operation. We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels. We then expand the operation space of several typical Neural Architecture Search (NAS) methods with the convolutions of large circular kernels. The searched new neural architectures do contain large circular kernels and outperform the original searched models considerably. Our additional analysis also reveals that large circular kernels could help the model to be more robust to the rotated or sheared images due to their better rotation invariance. Our work shows the potential of designing new convolutional kernels for CNNs, bringing up the prospect of expanding the search space of NAS with new variants of convolutions.
翻译:方内核是当代CNN的一个标准单元,因为它在卷发操作的变速计算中非常适合。然而,生物视觉系统中的视网膜交织细胞具有大致的共心容场。受此观察的驱使,我们提议使用带有同心和异向接受场的圆心内核作为卷发行动的选项。我们首先建议使用循环内核来简单而高效地实施卷动,并从经验上显示大型圆心内核在对应的平方内核上的巨大优势。我们的工作显示,有可能设计一些典型的神经结构搜索(NAS)方法与大型圆心内核交织在一起。搜索的新神经内核结构确实包含大型圆心内核,并大大超出原始搜索模型。我们的补充分析还表明,大型圆心内核可以帮助模型对旋转或剪切成的图像更加强大,因为它们的变换性更强。我们的工作显示,为CNNIS设计的新的神经内核内核研究(NAS)将带来新的空间搜索变异的前景。