Although CNNs are believed to be invariant to translations, recent works have shown this is not the case, due to aliasing effects that stem from downsampling layers. The existing architectural solutions to prevent aliasing are partial since they do not solve these effects, that originate in non-linearities. We propose an extended anti-aliasing method that tackles both downsampling and non-linear layers, thus creating truly alias-free, shift-invariant CNNs. We show that the presented model is invariant to integer as well as fractional (i.e., sub-pixel) translations, thus outperforming other shift-invariant methods in terms of robustness to adversarial translations.

翻译：虽然有线电视新闻网被认为不易翻译,但最近的著作表明情况并非如此,因为下层抽样层产生了别名效应。现有的防止别名的建筑解决方案是局部的,因为它们不能解决这些效应,这些效应源于非线性。我们建议扩大反丑化方法,既解决下层抽样问题,也解决非线性层问题,从而创造真正无别名、不移动的CNN。我们显示,所展示的模式是整数和分数(即次像素)翻译,因此在强力翻译到对立翻译方面优于其他变换方法。</s>