卷积神经网络如何处理混叠
How Convolutional Neural Networks Deal with Aliasing
摘要：
卷积神经网络（CNN）仍然是解决计算机视觉问题的重要工具。标准卷积架构由堆叠的操作层组成，这些操作层逐渐缩小图像尺寸。混叠是下采样可能发生的一种众所周知的副作用：它导致原始信号的高频分量与低频分量无法区分。虽然下采样发生在这些模型中的最大池化层或步幅卷积中，但没有明确的机制来防止这些层中发生混叠。由于这些模型令人印象深刻的性能，很自然地怀疑它们以某种方式隐含地处理了这种扭曲。我们在本文中要回答的问题很简单：“CNN如何以及在多大程度上抵消混叠？“我们通过两个例子来探讨这个问题：第一，我们评估了CNN区分输入振荡的能力，表明中间通道中的冗余在成功完成任务方面发挥了重要作用;在第二个，我们表明，图像分类器CNN，而在原则上，能够实现抗混叠滤波器，不能防止在中间层中发生混叠。
英文摘要：
The convolutional neural network (CNN) remains an essential tool in solving computer vision problems. Standard convolutional architectures consist of stacked layers of operations that progressively downscale the image. Aliasing is a well-known side-effect of downsampling that may take place: it causes high-frequency components of the original signal to become indistinguishable from its low-frequency components. While downsampling takes place in the max-pooling layers or in the strided-convolutions in these models, there is no explicit mechanism that prevents aliasing from taking place in these layers. Due to the impressive performance of these models, it is natural to suspect that they, somehow, implicitly deal with this distortion. The question we aim to answer in this paper is simply: "how and to what extent do CNNs counteract aliasing?" We explore the question by means of two examples: In the first, we assess the CNNs capability of distinguishing oscillations at the input, showing that the redundancies in the intermediate channels play an important role in succeeding at the task; In the second, we show that an image classifier CNN while, in principle, capable of implementing anti-aliasing filters, does not prevent aliasing from taking place in the intermediate layers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
