Modern convolutional networks are not shift-invariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and average-pooling, ignore the sampling theorem. The well-known signal processing fix is anti-aliasing by low-pass filtering before downsampling. However, simply inserting this module into deep networks degrades performance; as a result, it is seldomly used today. We show that when integrated correctly, it is compatible with existing architectural components, such as max-pooling and strided-convolution. We observe \textit{increased accuracy} in ImageNet classification, across several commonly-used architectures, such as ResNet, DenseNet, and MobileNet, indicating effective regularization. Furthermore, we observe \textit{better generalization}, in terms of stability and robustness to input corruptions. Our results demonstrate that this classical signal processing technique has been undeservingly overlooked in modern deep networks. Code and anti-aliased versions of popular networks are available at https://richzhang.github.io/antialiased-cnns/ .

翻译：现代革命网络不是易变的, 因为小输入变换或翻译可以导致产出的急剧变化。 常用的下游抽样方法, 如最大集合、 螺旋进化和平均集合, 忽略抽样理论。 众所周知的信号处理修补方法在下游取样之前通过低通道过滤器进行反诈骗。 但是, 简单地将这个模块插入深层网络会降低性能; 结果, 今天它很少被使用 。 我们显示, 当整合正确时, 它与现有的建筑部件相容, 如最大集合和螺旋进化。 我们观察图像网络分类中的\ textit{ 增加的精度, 在多个常用的架构中, 如 ResNet、 DenseNet 和 MobileNet, 显示有效的正规化。 此外, 我们观察了 kextititit{ better plicalization}, 在输入腐败的稳定性和稳健度方面, 。 我们的结果表明, 古典信号处理技术在现代深层网络中被忽略了。 代码 和反对的版本/ hangs. 。