Approach

Inception model

Two minor differences between and “extreme” version of an Inception module and a depthwise separable convolution would be：

• The order of the operations: depthwise separable convolutions as usually implemented perform first channel-wise spatial convolution and then perform 1x1 convolution, whereas Inception performs the 1x1 convolution first.
• The presence or absence of a non-linearity after the first operation. In Inception, both operations are followed by a ReLU non-linearity, however depthwise separable convolutions are usually implemented without non-linearities.

Experiment

We presented a novel architecture based on this idea, named Xception, which has a similar parameter count as Inception V3. Compared to Inception V3, Xception shows small gains in classification performance on the ImageNet dataset and large gains on the JFT dataset.

References：
Xception: Deep Learning with Depthwise Separable Convolutions， Francois Chollet， 2016，CVPR