Xception

Xception ("Extreme Inception") interprets the Inception module as an intermediate point on a continuum between an ordinary convolution and a fully decoupled spatial/channel filter. A standard Inception block splits the input into a few parallel branches, each of which is processed by a small $1\times1$ pointwise convolution followed by a spatial convolution, and the branch outputs are concatenated. Xception pushes this idea to its limit: instead of a handful of branches, every output channel of the $1\times1$ pointwise convolution gets its own independent $3\times3$ spatial filter. This is exactly the depthwise separable convolution — a pointwise mix in channel space followed by a per-channel spatial filter.

The architectural hypothesis is that the cross-channel correlations and the spatial correlations in feature maps are sufficiently decoupled that they can — and should — be modeled independently. A regular convolution conflates the two; a depthwise separable convolution separates them, dramatically reducing both the parameter count and the FLOPs:

Xception stacks 36 such layers, organised into 14 modules with linear residual shortcuts around each module (similar to ResNet). With essentially the same parameter budget as Inception-v3, it outperforms it on ImageNet and substantially outperforms it on the much larger JFT dataset. The architecture is designed for a $299 \times 299$ input — the same crop size as Inception-v3 — so the spatial-reduction schedule matches that of its predecessor exactly, isolating the depthwise-separable factorisation as the sole source of accuracy improvement.