Papers › Xception: Deep Learning with Depthwise Separable Convolutions

Xception: Deep Learning with Depthwise Separable Convolutions

7 Oct 2016CVPR 2017arXiv:1610.02357archive 2025-07-28

François 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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1610.02357")

Code

Syntology Ran 1 of 15 code samples harvested from 4 repositories linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: community (archive-listed): 15 samples from 4 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

41 repositories listed; official and paper-mentioned ones first.

2023-MindSpore-1/ms-code-205 mentioned on GitHubmindspore report
CharlieSergeant/pollen mentioned on GitHubLGPL-2.1 report
DarshanDeshpande/jax-models mentioned on GitHubjax report
IMvision12/keras-vision-models mentioned on GitHubpytorch report
LouisFoucard/w-net mentioned on GitHub report
TanyaChutani/Xception-Tf2.0 mentioned on GitHubtf report
Yohei-Kawakami/Bouquet mentioned on GitHub report
amogh7joshi/engagement-detection mentioned on GitHubtfMIT report
amogh7joshi/fer mentioned on GitHubtf report
bluejurand/Photos-colorization mentioned on GitHubtf report
ced-kin/dog-breed-ai mentioned on GitHubtf report
dbensoussan/rsna mentioned on GitHubpytorch report
drscotthawley/SPNet mentioned on GitHubtf report
hikapok/xception_tensorflow mentioned on GitHubtf report
i3p9/deepfake-detection-with-xception mentioned on GitHubpytorch report
kwotsin/TensorFlow-Xception mentioned on GitHubtfMIT report
marload/ConvNets-TensorFlow2 mentioned on GitHubtf report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
rwightman/pytorch-image-models mentioned on GitHubpytorch report
tanreinama/XceptionHourgrass---PyTorch mentioned on GitHubpytorch report
tensorflow/models mentioned on GitHubtf report
tensorflow/models mentioned on GitHubtf report
universvm/BacXeption mentioned on GitHubGPL-3.0 report
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

15 samples harvested; 1 ran; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
14unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

mish tanreinama/XceptionHourgrass---PyTorch/xceptionhourgrass.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 6a59ba4afdd39102 · report
apply_offsets amogh7joshi/engagement-detection/util/classifyimgops.py community (archive-listed) unverified MIT (permissive) · dffdd7167bf3ce15 · report
apply_with_random_selector kwotsin/TensorFlow-Xception/xception_preprocessing.py community (archive-listed) unverified MIT (permissive) · e82919ec054e8a8b · report
build_model_4 amogh7joshi/engagement-detection/models/pastmodels.py community (archive-listed) unverified MIT (permissive) · 43ba0b86d175e99c · report
create_model_5 amogh7joshi/engagement-detection/models/pastmodels.py community (archive-listed) unverified MIT (permissive) · 4a8e653ea8758e0d · report
create_model_6 amogh7joshi/engagement-detection/models/pastmodels.py community (archive-listed) unverified MIT (permissive) · c72c502fe2be8011 · report
distort_color kwotsin/TensorFlow-Xception/xception_preprocessing.py community (archive-listed) unverified MIT (permissive) · 7d9923a3d6958b99 · report
distorted_bounding_box_crop kwotsin/TensorFlow-Xception/xception_preprocessing.py community (archive-listed) unverified MIT (permissive) · f1bd3b4c3f92fe63 · report
grayscale amogh7joshi/engagement-detection/util/baseimgops.py community (archive-listed) unverified MIT (permissive) · 31c3c8cf7b95571f · report
load_json_model amogh7joshi/engagement-detection/models/model_factory.py community (archive-listed) unverified MIT (permissive) · 86ee540aa40f4d49 · report
load_keras_model amogh7joshi/engagement-detection/models/model_factory.py community (archive-listed) unverified MIT (permissive) · c739cc064f9fca4f · report
non_max_suppression amogh7joshi/engagement-detection/util/classifyimgops.py community (archive-listed) unverified MIT (permissive) · 6d593988bfb15f53 · report
preprocess_input amogh7joshi/engagement-detection/util/classifyimgops.py community (archive-listed) unverified MIT (permissive) · 51d8271eca5b94ff · report
reduced_kernel_size_for_small_input hikapok/xception_tensorflow/Xception.py community (archive-listed) unverified MIT (permissive) · 1d0c0051ecdfaf14 · report
resize amogh7joshi/engagement-detection/util/baseimgops.py community (archive-listed) unverified MIT (permissive) · c127f627ffe74343 · report

Tasks

ClassificationDeep LearningImage ClassificationSession-Based Recommendationsimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Classification InDL Xception Average Recall 89.81% #5 of 9 Archive leaderboard report
Image Classification ImageNet Xception Hardware Burden 87G #793 of 1060 Archive leaderboard report
Image Classification ImageNet Xception Number of params 22.855952M #793 of 1060 Archive leaderboard report
Image Classification ImageNet Xception Operations per network pass 0.838G #793 of 1060 Archive leaderboard report
Image Classification ImageNet Xception Top 1 Accuracy 79% #793 of 1060 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

1x1 ConvolutionAverage PoolingConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGlobal Average PoolingInception ModuleMax PoolingPointwise ConvolutionRMSPropReLUResidual ConnectionSGD with MomentumSoftmaxStep DecayWeight Decay

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