论文标题
CNN的空间转换不足以支持不变识别
Inability of spatial transformations of CNN feature maps to support invariant recognition
论文作者
论文摘要
许多深度学习体系结构都使用CNN功能图或过滤器的空间转换来更好地处理由自然图像转换引起的对象外观的可变性。在本文中，我们证明，CNN特征图的空间变换无法对齐转换的图像的特征图，以匹配其原始图像，除非提取的特征本身是不变的，否则将其与原始图像相匹配。我们的证明是基于单层和多层网络案例的基本分析。结果表明，基于CNN特征图或过滤器的空间变换的方法无法替换输入的图像对齐，并且无法实现对一般仿射变换的不变识别，特别是用于缩放转换或剪切转换。对于旋转和反射，在空间转换特征图或过滤器可以实现不变性，但仅适用于具有学习或硬编码的旋转或反射不变特征的网络
A large number of deep learning architectures use spatial transformations of CNN feature maps or filters to better deal with variability in object appearance caused by natural image transformations. In this paper, we prove that spatial transformations of CNN feature maps cannot align the feature maps of a transformed image to match those of its original, for general affine transformations, unless the extracted features are themselves invariant. Our proof is based on elementary analysis for both the single- and multi-layer network case. The results imply that methods based on spatial transformations of CNN feature maps or filters cannot replace image alignment of the input and cannot enable invariant recognition for general affine transformations, specifically not for scaling transformations or shear transformations. For rotations and reflections, spatially transforming feature maps or filters can enable invariance but only for networks with learnt or hardcoded rotation- or reflection-invariant features
