We present an interpretation of Inception modules in convolutional neural
networks as being an intermediate step in-between regular convolution and the
depthwise separable convolution operation (a depthwise convolution followed by
a pointwise convolution). In this light, a depthwise separable convolution can
be understood as an Inception module with a maximally large number of towers.
This observation leads us to propose a novel deep convolutional neural network
architecture inspired by Inception, where Inception modules have been replaced
with depthwise separable convolutions. We show that this architecture, dubbed
Xception, slightly outperforms Inception V3 on the ImageNet dataset (which
Inception V3 was designed for), and significantly outperforms Inception V3 on a
larger image classification dataset comprising 350 million images and 17,000
classes. Since the Xception architecture has the same number of parameters as
Inception V3, the performance gains are not due to increased capacity but
rather to a more efficient use of model parameters.

这篇论文介绍了卷积神经网络中 Inception 模块的解释和中间步骤，提出了一种新的深层卷积神经网络架构 Xception 来替换 Inception 模块，它在 ImageNet 数据集上的表现略优于 Inception V3，但在包括 350 万张图像和 17,000 个类别的更大的图像分类数据集上表现显著优于 Inception V3，并说明这种性能提升不是由于增加的参数容量，而是由于模型参数的更有效使用。