Papers › Xception: Deep Learning With Depthwise Separable Convolutions

Xception: Deep Learning With Depthwise Separable Convolutions

1 Jul 2017CVPR 2017 7archive 2025-07-28

Francois Chollet

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.

PaperPDFCode

Code

PaddlePaddle/PaddleClas paddleApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep LearningImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Retinal OCT Disease Classification OCT2017 Xception Sensitivity 99.7 #16 of 16 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 Xception Acc 99.36 #4 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Depthwise Separable Convolution

1x1 ConvolutionAverage PoolingConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingInception ModuleMax PoolingPointwise ConvolutionReLUResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections