论文标题
使用STN对齐CNN功能图的问题
The problems with using STNs to align CNN feature maps
论文作者
论文摘要
空间变压器网络（STN）旨在使CNN能够学习不变性以形象转换。最初提出了STN来改变CNN特征图和输入图像。这可以在预测转换参数时使用更复杂的功能。但是，由于STN进行了纯粹的空间转换，因此，在一般情况下，它们无法将转换图像及其原始图像的特征图对齐。我们为此提出了一个理论上的论点，并研究了实际含义，表明这种无能与分类精度降低相结合。我们主张利用更深层中更复杂的特征，而不是在分类和本地化网络之间共享参数。
Spatial transformer networks (STNs) were designed to enable CNNs to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables the use of more complex features when predicting transformation parameters. However, since STNs perform a purely spatial transformation, they do not, in the general case, have the ability to align the feature maps of a transformed image and its original. We present a theoretical argument for this and investigate the practical implications, showing that this inability is coupled with decreased classification accuracy. We advocate taking advantage of more complex features in deeper layers by instead sharing parameters between the classification and the localisation network.
