Papers › Xception: Deep Learning with Depthwise Separable Convolutions
Xception: Deep Learning with Depthwise Separable Convolutions
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1610.02357")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1610.02357", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1610.02357")
Code
Syntology 15 code samples harvested from 4 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 15 samples from 4 repositories, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 10 of its repositories that Syntology harvested for other papers:
- DarshanDeshpande/jax-models, community (archive-listed): harvested for 8 other papers, listed under the repository
- IMvision12/keras-vision-models, community (archive-listed): harvested for another paper, listed under the repository
- amogh7joshi/fer, community (archive-listed): harvested for another paper, listed under the repository
- bluejurand/Photos-colorization, community (archive-listed): harvested for another paper, listed under the repository
- crowdAI/crowdai-musical-genre-recognition-starter-kit, community (archive-listed): harvested for another paper, listed under the repository
- marload/ConvNets-TensorFlow2, community (archive-listed): harvested for 3 other papers, listed under the repository
- osmr/imgclsmob, community (archive-listed): harvested for another paper, listed under the repository
- rwightman/pytorch-image-models, community (archive-listed): harvested for another paper, listed under the repository
- tensorflow/models, community (archive-listed): harvested for 4 other papers, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.
41 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
15 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
4a8e653ea8758e0d · report
fixture: signature input:tuple/1/int, classes:int/0/int, l2_reg:float/0/float · returned Functional · level recorded 2026-09-26 31c3c8cf7b95571f · report
fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-26 c739cc064f9fca4f · report
fixture: signature model_name:str/0/str, folder_path:str/0/str, weights_format:NoneType/0/?, compile:str/0/str · returned Functional · level recorded 2026-09-26 6d593988bfb15f53 · report
fixture: signature rects:ndarray/2/int, overlap_thresh:float/0/float · returned ndarray · level recorded 2026-09-26 51d8271eca5b94ff · report
fixture: signature x:ndarray/4/int, v2:bool/0/bool · returned ndarray · level recorded 2026-09-26 census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket util/baseimgops.py ran MIT (permissive) ·
c127f627ffe74343 · report
fixture: signature img:ndarray/2/int, target_shape:tuple/1/int · returned ndarray · level recorded 2026-09-26 1d0c0051ecdfaf14 · report
e82919ec054e8a8b · report
7d9923a3d6958b99 · report
f1bd3b4c3f92fe63 · report
census: 5 implementations from 8 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 xceptionhourgrass.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) ·
6a59ba4afdd39102 · report
fixture: returned Tensor · level recorded, date not recorded Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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