论文标题
关于CNN中的翻译不变性：卷积层可以利用绝对空间位置
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
论文作者
论文摘要
在本文中，我们挑战了一个普遍的假设，即现代CNN中的卷积层是翻译不变的。我们表明，CNN可以并且将通过学习通过利用图像边界效应对特定绝对位置做出响应的过滤器来利用绝对空间位置。由于现代CNN滤波器具有巨大的接收场，因此这些边界效应甚至远离图像边界，从而使网络可以在整个图像上利用绝对空间位置。我们提供了一个简单的解决方案来删除空间位置编码，从而改善了翻译不变性，从而提供了更强的视觉感应偏置，特别有益于小型数据集。我们在几个架构和各种应用程序（例如图像分类，补丁匹配和两个视频分类数据集）上广泛证明了这些好处。
In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to particular absolute locations by exploiting image boundary effects. Because modern CNNs filters have a huge receptive field, these boundary effects operate even far from the image boundary, allowing the network to exploit absolute spatial location all over the image. We give a simple solution to remove spatial location encoding which improves translation invariance and thus gives a stronger visual inductive bias which particularly benefits small data sets. We broadly demonstrate these benefits on several architectures and various applications such as image classification, patch matching, and two video classification datasets.
