Papers › Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

7 Feb 2018ECCV 2018 9arXiv:1802.02611archive 2025-07-28

Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https://github.com/tensorflow/models/tree/master/research/deeplab.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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):

Code

No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 72 samples below come from 17 community repositories. Syntology harvested code from tensorflow/models for 4 other papers.

tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 72 code samples harvested from 17 repositories linked to this paper: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 72 samples from 17 repositories, 44 ran (28 with no instrument failure; 16 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 17 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

tensorflow/models officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
AtrayeeNag/Image-Segmentation-deeplabv3 mentioned on GitHubtfSyntology: not harvested report
AutomatedAI/deeplab_inference mentioned on GitHubtfSyntology: not harvested report
AutomatedAI/deeplab_segmentation_example mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
EdwinAlegria/object_semantic_deeplabv3 mentioned on GitHubtfSyntology: not harvested report
Gregor-Mendel-Institute/aradeepopsis mentioned on GitHubtfSyntology: not harvested report
GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet mentioned on GitHubpaddleSyntology: not harvested report
JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models mentioned on GitHubtfSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
JinyongJeong/DeeplabV3_Apolloscape_and_CityScape mentioned on GitHubtfSyntology: not harvested report
MukhlasAdib/KITTI_Mapping mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Popcorn-sugar/Deep_v2 mentioned on GitHubtfSyntology: not harvested report
PuchatekwSzortach/voc_encoder_decoder_with_atrous_separable_convolutions mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Robinatp/Deeplab_Tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Atrous Convolution for Semantic Image Segmentation (arXiv:1706.05587; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
SkyWa7ch3r/ImageSegmentation mentioned on GitHubtfSyntology: not harvested report
SkyWa7ch3r/SceneSegmentation mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Syarujianai/deeplab-commented mentioned on GitHubtfSyntology: not harvested report
VainF/DeepLabV3Plus-Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Atrous Convolution for Semantic Image Segmentation (arXiv:1706.05587; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Vignesh-95/cnn-semantic-segmentation-satellite-images mentioned on GitHubtfSyntology: not harvested report
Vujas-Eteph/CiVOS mentioned on GitHubpytorchSyntology: 17 samples, 10 ran (3 instrument-failed) · 7 unverified report
abhishekdbihani/MudrockNet mentioned on GitHubtfSyntology: not harvested report
ayoolaolafenwa/PixelLib mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointRend: Image Segmentation as Rendering (arXiv:1912.08193; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
branislavhesko/segmentation_framework mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
chenmengyang/rename_later mentioned on GitHubSyntology: not harvested report
chuhan89/wsss-tissue mentioned on GitHubpytorchSyntology: not harvested report
czarmanu/sentinel_lakeice mentioned on GitHubtfSyntology: not harvested report
developmentseed/looking-glass-pub mentioned on GitHubtfSyntology: not harvested report
dootmaan/dsrl mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
ensta-u2is/deeplabv3plus-muad-pytorch mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
giannifranchi/deeplabv3-superpixelmix mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Atrous Convolution for Semantic Image Segmentation (arXiv:1706.05587; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
giovanniguidi/deeplabV3-PyTorch mentioned on GitHubpytorchSyntology: 7 samples, 2 ran (2 instrument-failed) · 5 unverified report
giovanniguidi/deeplabV3_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
heidongxianhau/deeplab2 mentioned on GitHubtfSyntology: not harvested report
jfzhang95/pytorch-deeplab-xception mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
kaichoulyc/course_segmentation mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
kawausomando/green_vegetation_v2 mentioned on GitHubtfSyntology: not harvested report
kekeller/semantic_soy_deeplabv3plus mentioned on GitHubtfSyntology: not harvested report
lattice-ai/DeepLabV3-Plus mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
leimao/DeepLab-V3 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,... (arXiv:1606.00915; that paper's own run record: 43 ran (of which 12 constructed an object rather than computing a result; 35 with no instrument failure: 1 honoured, 0 violated, 34 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
leimao/DeepLab_v3 mentioned on GitHubtfSyntology: not harvested report
mathildor/DeepLab-v3 mentioned on GitHubtfSyntology: not harvested report
mlearing/pytorch-deeplab-v3-plus mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (1 instrument-failed) · 1 unverified report
nolanliou/PeopleSegmentationDemo mentioned on GitHubtfSyntology: not harvested report
parachutel/deeplabv3plus_on_Mapillary_Vistas mentioned on GitHubtfSyntology: not harvested report
petko-nikolov/pysemseg mentioned on GitHubpytorchSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
phue/aradeepopsis mentioned on GitHubtfSyntology: not harvested report
pideyi1025/DeepLabV3Plus-RailSem19 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking BiSeNet For Real-time Semantic Segmentation (arXiv:2104.13188; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
rishizek/tensorflow-deeplab-v3-plus mentioned on GitHubtfSyntology: not harvested report
saehan-choi/pixellib_auto_labelling mentioned on GitHubpytorchMITSyntology: not harvested report
samson6460/tf2_Segmentation mentioned on GitHubtfSyntology: 5 samples, 3 ran (3 instrument-failed) · 2 unverified report
samson6460/tf2_pose_estimation mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
sara-nl/SURF-deeplab mentioned on GitHubtfSyntology: not harvested report
sara-nl/SURF-segmentation mentioned on GitHubtfSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report
shanglianlm0525/CvPytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
sharifelguindi/DeepLab mentioned on GitHubtfSyntology: not harvested report
shenshutao/image_segmentation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
soumik12345/DeepLabV3-Plus mentioned on GitHubtfSyntology: not harvested report
tantara/JejuNet mentioned on GitHubtfSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
ucuapps/WSMIS mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
wang-wg/DeepStroke mentioned on GitHubtfSyntology: not harvested report
wangyi111/international-archaeology-ai-challenge mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
y-ouali/pytorch_segmentation mentioned on GitHubpytorchSyntology: not harvested report
zhuang42/csc420 mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-224 mindsporeSyntology: not harvested report
Burf/tfdetection tfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
Media-Smart/vedaseg pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified) and DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,... (arXiv:1606.00915; that paper's own run record: 43 ran (of which 12 constructed an object rather than computing a result; 35 with no instrument failure: 1 honoured, 0 violated, 34 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
MegEngine/Models Syntology: not harvested report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-paper-code-2/code400 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code400 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
TanyaChutani/DeepLabV3Plus-Tf2.0 tfSyntology: not harvested report
bonlime/keras-deeplab-v3-plus tfSyntology: not harvested report
mindspore-ai/models mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmsegmentation pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Perceptual Artifacts Localization for Image Synthesis Tasks (arXiv:2310.05590; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

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

72 samples harvested: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 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.

2ran · honoured contract
10ran · our draft was wrong
6ran; the contract check could not run
26ran
28unverified

Licence: 40 of the 72 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 17 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”. For 9 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
AtrousSeparableConvolutionBnReLU tensorflow_advanced_segmentation_models/models/DeepLabV3plus.py ran licence not identified · pointer only · 03d31a466787b052 · report fixture: returned AtrousSeparableConvolutionBnReLU · level recorded 2026-09-22
ConvolutionBnActivation tensorflow_advanced_segmentation_models/models/DeepLabV3plus.py ran licence not identified · pointer only · 3326d9cd4c357d28 · report fixture: returned ConvolutionBnActivation · level recorded 2026-09-22
AtrousSpatialPyramidPoolingV3 tensorflow_advanced_segmentation_models/models/DeepLabV3plus.py unverified licence not identified · pointer only · a9f549942de7d30b · report
DeepLabV3plus tensorflow_advanced_segmentation_models/models/DeepLabV3plus.py unverified licence not identified · pointer only · 63a49a3c1dd4d263 · report
MukhlasAdib/KITTI_Mapping community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
segmentation_inference app/pipeline/road_segmentation.py ran no licence file found · pointer only · b1992cb92fab6136 · report fixture: signature img_in:ndarray/3/int, sess:MockSession/0/?, target_size:int/0/int, probability_threshold:float/0/float · returned tuple · level recorded 2026-09-25
RoadSegmentation app/pipeline/road_segmentation.py unverified no licence file found · pointer only · 82f03ca51ba7dbc4 · report
PuchatekwSzortach/voc_encoder_decoder_with_atrous_separable_convolutions community (archive-listed) 1 sample, 0 ran · 1 unverified
DeepLabV3PlusBuilder net/ml.py unverified MIT (permissive) · 9755f047bfec69ce · report
SkyWa7ch3r/SceneSegmentation community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
ASPP in 23 papers deeplabv3plus.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 0f94e0514fb25366 · report fixture: signature inputs:EagerTensor/4/float, depthwise:bool/0/bool, output_stride:int/0/int · returned EagerTensor · level recorded 2026-09-22
Vujas-Eteph/CiVOS community (archive-listed) 17 samples, 10 ran (3 instrument-failed) · 7 unverified
BasicBlockV1b RiTM/isegm/model/modeling/deeplab_v3.py ran BSD-3-Clause (permissive) · 1e87570d52719052 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
BottleneckV1b RiTM/isegm/model/modeling/deeplab_v3.py ran · metamorphic tier: invariant BSD-3-Clause (permissive) · 43562ef9d87c54e7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SeparableConv2d in 5 papers RiTM/isegm/model/modeling/deeplab_v3.py ran fingerprinted BSD-3-Clause (permissive) · 414adf534687df82 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
_ASPP RiTM/isegm/model/modeling/deeplab_v3.py ran · metamorphic tier: invariant fingerprinted BSD-3-Clause (permissive) · ebedb218ce19918d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_ASPPConv RiTM/isegm/model/modeling/deeplab_v3.py ran · our draft was wrong BSD-3-Clause (permissive) · 3274a200ef8fa29a · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, atrous_rate:int/0/int, norm_layer:callable/0/? · returned Sequential · level recorded 2026-09-22
_AsppPooling RiTM/isegm/model/modeling/deeplab_v3.py ran · metamorphic tier: invariant fingerprinted BSD-3-Clause (permissive) · d5caae9d47ff2394 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_DeepLabHead RiTM/isegm/model/modeling/deeplab_v3.py ran fingerprinted BSD-3-Clause (permissive) · a5651a6111de513f · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
_SkipProject RiTM/isegm/model/modeling/deeplab_v3.py ran · metamorphic tier: invariant fingerprinted BSD-3-Clause (permissive) · 9c74246baf89e0d2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_safe_state_dict_filtering RiTM/isegm/model/modeling/deeplab_v3.py ran · our draft was wrong BSD-3-Clause (permissive) · 5776a2cbccc2bd40 · report fixture: signature orig_dict:dict/0/?, model_dict_keys:set/0/? · returned dict · level recorded 2026-09-24
select_activation_function RiTM/isegm/model/modeling/deeplab_v3.py ran · our draft was wrong BSD-3-Clause (permissive) · 4976637b084e5281 · report fixture: signature activation:str/0/str · returned type · level recorded 2026-09-22
DeepLabV3Plus RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · 609cfe0df52cf002 · report
ResNetBackbone in 10 papers RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · fabf7df16100c5bc · report
ResNetV1b RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · 96875ada06fa67da · report
resnet101_v1s RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · 7a0b3803f28d47fa · report
resnet152_v1s RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · d9691f627c30dde9 · report
resnet34_v1b RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · 602a54842f95f3f0 · report
resnet50_v1s RiTM/isegm/model/modeling/deeplab_v3.py unverified BSD-3-Clause (permissive) · 3222e50cba4be935 · report
dootmaan/dsrl community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
build_sr_decoder modeling/deeplab.py ran · our draft was wrong MIT (permissive) · 6d5672a93099e8b5 · report fixture: signature num_classes:int/0/int, backbone:str/0/str, BatchNorm:callable/0/? · returned Decoder · level recorded 2026-09-24
DeepLab modeling/deeplab.py unverified MIT (permissive) · 9ac514a69bb5bb62 · report
ensta-u2is/deeplabv3plus-muad-pytorch community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
ASPP in 23 papers network/_deeplab.py ran fingerprinted MIT (permissive) · 9a5496117125b307 · report fixture: returned ASPP · level recorded 2026-09-22
ASPPConv in 9 papers network/_deeplab.py ran fingerprinted MIT (permissive) · eaa0ac6ed86c450b · report fixture: returned ASPPConv · level recorded 2026-09-22
ASPPPooling in 6 papers network/_deeplab.py ran fingerprinted MIT (permissive) · cb6b44750325dc1e · report fixture: returned ASPPPooling · level recorded 2026-09-22
DeepLabHeadV3Plus network/_deeplab.py ran MIT (permissive) · fc4e40cedd008787 · report fixture: returned DeepLabHeadV3Plus · level recorded 2026-09-22
giovanniguidi/deeplabV3-PyTorch community (archive-listed) 7 samples, 2 ran (2 instrument-failed) · 5 unverified
build_aspp in 10 papers models/deeplab.py ran · our draft was wrong no licence file found · pointer only · 68330450cf875f58 · report fixture: signature backbone:str/0/str, output_stride:int/0/int, BatchNorm:callable/0/? · returned ASPP · level recorded 2026-09-22
build_decoder in 18 papers models/deeplab.py ran · our draft was wrong no licence file found · pointer only · 3f8ff8379eaf97df · report fixture: signature num_classes:int/0/int, backbone:str/0/str, BatchNorm:callable/0/? · returned Decoder · level recorded 2026-09-22
ASPP in 23 papers models/deeplab.py unverified no licence file found · pointer only · 26047a3c90df0a36 · report
Decoder in 210 papers models/deeplab.py unverified no licence file found · pointer only · edf673cbd75a7027 · report
DeepLab models/deeplab.py unverified no licence file found · pointer only · 4ac4bc7c6f72419c · report
_ASPPModule in 7 papers models/deeplab.py unverified no licence file found · pointer only · 350abbaf676488bc · report
build_backbone in 29 papers models/deeplab.py unverified no licence file found · pointer only · d4f09015805919e2 · report
jfzhang95/pytorch-deeplab-xception community (archive-listed) 1 sample, 0 ran · 1 unverified
DeepLab modeling/deeplab.py unverified MIT (permissive) · 09a240d3865fee6c · report
kaichoulyc/course_segmentation community (archive-listed) 1 sample, 0 ran · 1 unverified
DeepLab model/deep_lab/deeplab.py unverified no licence file found · pointer only · 6e6115c04c3f121d · report
lattice-ai/DeepLabV3-Plus community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
AtrousSpatialPyramidPooling deeplabv3plus/model/deeplabv3_plus.py ran no licence file found · pointer only · 4a9a634b49dda7a4 · report fixture: returned AtrousSpatialPyramidPooling · level recorded 2026-09-22
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
deeplabv3plus/model/deeplabv3_plus.py ran fingerprinted no licence file found · pointer only · 692e7f2e56fbd23e · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
DeeplabV3Plus deeplabv3plus/model/deeplabv3_plus.py unverified no licence file found · pointer only · 59849f10377fad5f · report
mlearing/pytorch-deeplab-v3-plus community (archive-listed) 5 samples, 4 ran (1 instrument-failed) · 1 unverified
ASPP_module networks/deeplab_resnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a4f0a021c8fd4295 · report fixture: returned ASPP_module · level recorded 2026-09-22
Bottleneck in 98 papers networks/deeplab_resnet.py ran · metamorphic tier: deterministic MIT (permissive) · 682f6d56a1c45f69 · report fixture: returned Bottleneck · level recorded 2026-09-22
ResNet in 139 papers networks/deeplab_resnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 42610493d6f82abe · report fixture: returned ResNet · level recorded 2026-09-22
ResNet101 in 11 papers networks/deeplab_resnet.py ran · our draft was wrong MIT (permissive) · 5b3058ed46740fef · report fixture: signature nInputChannels:int/0/int, os:int/0/int, pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-22
DeepLabv3_plus networks/deeplab_resnet.py unverified MIT (permissive) · dfd28692d87464d1 · report
petko-nikolov/pysemseg community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
ASPPModule pysemseg/models/deeplab.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 0633b0a6570b756e · report fixture: returned ASPPModule · level recorded 2026-09-22
Bottleneck in 98 papers pysemseg/models/deeplab.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · df2ed20fe3290ced · report fixture: returned Bottleneck · level recorded 2026-09-22
Decoder in 210 papers pysemseg/models/deeplab.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 303dec08f3ebd517 · report fixture: returned Decoder · level recorded 2026-09-22
Deeplab in 7 papers pysemseg/models/deeplab.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · c10a37b7673d30e0 · report fixture: returned Deeplab · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
pysemseg/models/deeplab.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · d99dfd9a3f26d56b · report fixture: returned ResBlock · level recorded 2026-09-22
ResNet in 139 papers pysemseg/models/deeplab.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 8e495c6bb6122711 · report fixture: returned ResNet · level recorded 2026-09-22
resnet in 17 papers pysemseg/models/deeplab.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 90c8dc399d2c6b51 · report fixture: signature layers:list/1/int, pretrained_model:NoneType/0/?, in_channels:int/0/int, output_stride:int/0/int, multi_grid:tuple/1/int, add_blocks:int/0/int · returned ResNet · level recorded 2026-09-22
deeplabv3plus_resnet101 pysemseg/models/deeplab.py unverified GPL-3.0 (copyleft) · pointer only · 83604720aed3cccf · report
resnet101 in 24 papers pysemseg/models/deeplab.py unverified GPL-3.0 (copyleft) · pointer only · c5fb690670bbe8da · report
samson6460/tf2_Segmentation community (archive-listed) 5 samples, 3 ran (3 instrument-failed) · 2 unverified
SepConv_BN models/deep_lab_model.py ran · our draft was wrong no licence file found · pointer only · e6cccdb5cc9404d7 · report fixture: signature x:KerasTensor/0/float, filters:int/0/int, prefix:str/0/str, stride:int/0/int, kernel_size:int/0/int, rate:int/0/int, depth_activation:bool/0/bool, epsilon:float/0/float · returned KerasTensor · level recorded 2026-09-22
_conv2d_same models/deep_lab_model.py ran · our draft was wrong no licence file found · pointer only · 1096e5ba9c24632c · report fixture: signature x:KerasTensor/0/float, filters:int/0/int, prefix:str/0/str, stride:int/0/int, kernel_size:int/0/int, rate:int/0/int · returned KerasTensor · level recorded 2026-09-22
_xception_block models/deep_lab_model.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 398cd429c73d683e · report fixture: signature inputs:EagerTensor/4/float, depth_list:list/1/int, prefix:str/0/str, skip_connection_type:str/0/str, stride:int/0/int, rate:int/0/int, depth_activation:bool/0/bool, return_skip:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
_inverted_res_block models/deep_lab_model.py unverified no licence file found · pointer only · c4e00178c12b2cf8 · report
deeplabv3 models/deep_lab_model.py unverified no licence file found · pointer only · 8be86acb174d9241 · report
samson6460/tf2_pose_estimation community (archive-listed) 1 sample, 0 ran · 1 unverified
deeplabv3 models/deep_lab_model.py unverified no licence file found · pointer only · 66b9a9d2e9d2ca8d · report
sara-nl/SURF-segmentation community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
SepConv_BN deeplab/keras-deeplab-v3-plus-master/model.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · b293f1d81655c5e6 · report fixture: signature x:EagerTensor/4/float, filters:int/0/int, prefix:str/0/str, stride:int/0/int, kernel_size:int/0/int, rate:int/0/int, depth_activation:bool/0/bool, epsilon:float/0/float · returned EagerTensor · level recorded 2026-09-22
_conv2d_same deeplab/keras-deeplab-v3-plus-master/model.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 3ebb19f692e505f6 · report fixture: signature x:EagerTensor/4/float, filters:int/0/int, prefix:str/0/str, stride:int/0/int, kernel_size:int/0/int, rate:int/0/int · returned EagerTensor · level recorded 2026-09-22
_make_divisible in 9 papers deeplab/keras-deeplab-v3-plus-master/model.py ran · honoured contract no licence file found · pointer only · 1eac80b6e2cee7b2 · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22
_xception_block deeplab/keras-deeplab-v3-plus-master/model.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 76185251accca7d2 · report fixture: signature inputs:KerasTensor/4/float, depth_list:list/1/int, prefix:str/0/str, skip_connection_type:str/0/str, stride:int/0/int, rate:int/0/int, depth_activation:bool/0/bool, return_skip:bool/0/bool · returned KerasTensor · level recorded 2026-09-22
relu6 in 14 papers deeplab/keras-deeplab-v3-plus-master/model.py ran · honoured contract fingerprinted no licence file found · pointer only · e7a210769e38826c · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-22
Deeplabv3 deeplab/keras-deeplab-v3-plus-master/model.py unverified no licence file found · pointer only · 13a67fcfc1e4c1d7 · report
_inverted_res_block deeplab/keras-deeplab-v3-plus-master/model.py unverified no licence file found · pointer only · f52f02f15632fc39 · report
Burf/tfdetection community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
AtrousSpatialPyramidPooling tfdet/model/head/deeplab.py ran Apache-2.0 (permissive) · a2f1b4aadd626233 · report fixture: returned AtrousSpatialPyramidPooling · level recorded 2026-09-22
conv in 178 papers tfdet/model/head/deeplab.py ran · our draft was wrong Apache-2.0 (permissive) · b387bf7cf1bc8ced · report fixture: signature filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str, use_bias:bool/0/bool, kernel_initializer:str/0/str · returned Conv2D · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

18 assemblies on this paper: 18 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

18 sibling assemblies for DeepLabv3+ (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 18 sibling assemblies; the other 6 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLabv3_plus entry · level 0 · unverified · dfd28692d87464d1
  2. ASPP_module model · level 1 · ran · a4f0a021c8fd4295
  3. ResNet101 helper · level 1 · ran · our draft was wrong · 5b3058ed46740fef
  4. Bottleneck model · level 1 · ran · 682f6d56a1c45f69
  5. ResNet model · level 1 · ran · 42610493d6f82abe

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLabV3PlusBuilder entry · level 0 · unverified · 9755f047bfec69ce

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 7 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. Deeplabv3 entry · level 0 · unverified · 13a67fcfc1e4c1d7
  2. SepConv_BN model · level 1 · ran; the contract check could not run (RAISES) · b293f1d81655c5e6
  3. _conv2d_same model · level 1 · ran; the contract check could not run (RAISES) · 3ebb19f692e505f6
  4. _inverted_res_block model · level 0 · unverified · f52f02f15632fc39
  5. _make_divisible helper · level 1 · ran · honoured contract · 1eac80b6e2cee7b2
  6. _xception_block model · level 1 · ran; the contract check could not run (RAISES) · 76185251accca7d2
  7. relu6 helper · level 1 · ran · honoured contract · e7a210769e38826c

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 9 bricks; individually on a fixture: 7 ran (of which 6 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) · 2 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. deeplabv3plus_resnet101 entry · level 0 · unverified · 83604720aed3cccf
  2. Decoder model · level 1 · ran · 303dec08f3ebd517
  3. Deeplab model · level 1 · ran · c10a37b7673d30e0
  4. resnet101 model · level 0 · unverified · c5fb690670bbe8da
  5. ASPPModule helper · level 1 · ran · 0633b0a6570b756e
  6. resnet helper · level 1 · ran; the contract check could not run (RAISES) · 90c8dc399d2c6b51
  7. ResNet helper · level 1 · ran · 8e495c6bb6122711
  8. ResBlock helper · level 1 · ran · d99dfd9a3f26d56b
  9. Bottleneck helper · level 1 · ran · df2ed20fe3290ced

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 14 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLab entry · level 0 · unverified · 4ac4bc7c6f72419c
  2. SynchronizedBatchNorm2d helper · level 1 · ran · e6f91e80712a76dd
  3. build_aspp helper · level 1 · ran · our draft was wrong · 68330450cf875f58
  4. build_backbone helper · level 0 · unverified · d4f09015805919e2
  5. build_decoder helper · level 1 · ran · our draft was wrong · 3f8ff8379eaf97df
  6. _SynchronizedBatchNorm helper · level 1 · ran · 9f557ce8389a603f
  7. ASPP model · level 0 · unverified · 26047a3c90df0a36
  8. Decoder model · level 0 · unverified · edf673cbd75a7027
  9. SyncMaster helper · level 1 · ran · 93f1be24e0653bc8
  10. _sum_ft helper · level 1 · ran · violated contract · 3151cee68a1020dc
  11. _unsqueeze_ft helper · level 1 · ran · honoured contract · 1efd43bcf31727c0
  12. _ASPPModule helper · level 0 · unverified · 350abbaf676488bc
  13. FutureResult helper · level 1 · ran · 9e8c636cac1d847f
  14. SlavePipe helper · level 1 · ran · e75aa93b78286d50

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 14 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLab entry · level 0 · unverified · 6e6115c04c3f121d
  2. SynchronizedBatchNorm2d helper · level 1 · ran · e6f91e80712a76dd
  3. build_aspp helper · level 1 · ran · our draft was wrong · 68330450cf875f58
  4. build_backbone helper · level 0 · unverified · d4f09015805919e2
  5. build_decoder helper · level 1 · ran · our draft was wrong · 3f8ff8379eaf97df
  6. _SynchronizedBatchNorm helper · level 1 · ran · 9f557ce8389a603f
  7. ASPP model · level 0 · unverified · 26047a3c90df0a36
  8. Decoder model · level 0 · unverified · edf673cbd75a7027
  9. SyncMaster helper · level 1 · ran · 93f1be24e0653bc8
  10. _sum_ft helper · level 1 · ran · violated contract · 3151cee68a1020dc
  11. _unsqueeze_ft helper · level 1 · ran · honoured contract · 1efd43bcf31727c0
  12. _ASPPModule helper · level 0 · unverified · 350abbaf676488bc
  13. FutureResult helper · level 1 · ran · 9e8c636cac1d847f
  14. SlavePipe helper · level 1 · ran · e75aa93b78286d50

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. AtrousSpatialPyramidPooling entry · level 1 · ran · a2f1b4aadd626233
  2. conv helper · level 1 · ran · our draft was wrong · b387bf7cf1bc8ced
  3. normalize helper · level 1 · ran · our draft was wrong · 95a4808f923054e2

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeeplabV3Plus entry · level 0 · unverified · 59849f10377fad5f
  2. AtrousSpatialPyramidPooling model · level 1 · ran · 4a9a634b49dda7a4
  3. ConvBlock model · level 1 · ran · 692e7f2e56fbd23e

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 4 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLabV3plus entry · level 0 · unverified · 63a49a3c1dd4d263
  2. AtrousSeparableConvolutionBnReLU model · level 1 · ran · 03d31a466787b052
  3. AtrousSpatialPyramidPoolingV3 model · level 0 · unverified · a9f549942de7d30b
  4. ConvolutionBnActivation helper · level 1 · ran · 3326d9cd4c357d28

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLabHeadV3Plus entry · level 1 · ran · fc4e40cedd008787
  2. ASPP model · level 1 · ran · 9a5496117125b307
  3. ASPPConv helper · level 1 · ran · eaa0ac6ed86c450b
  4. ASPPPooling helper · level 1 · ran · cb6b44750325dc1e

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 6 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. deeplabv3 entry · level 0 · unverified · 8be86acb174d9241
  2. SepConv_BN model · level 1 · ran · our draft was wrong · e6cccdb5cc9404d7
  3. _conv2d_same helper · level 1 · ran · our draft was wrong · 1096e5ba9c24632c
  4. _inverted_res_block model · level 0 · unverified · c4e00178c12b2cf8
  5. _make_divisible helper · level 1 · ran · honoured contract · 1eac80b6e2cee7b2
  6. _xception_block model · level 1 · ran; the contract check could not run (RAISES) · 398cd429c73d683e

harvested Assembly for DeepLabv3+ (graph method: DeepLabv3+). 16 bricks; individually on a fixture: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. DeepLab entry · level 0 · unverified · 9ac514a69bb5bb62
  2. EDSRConv helper · level 1 · ran · 3a07013be7ddb70a
  3. SynchronizedBatchNorm2d helper · level 1 · ran · e6f91e80712a76dd
  4. build_aspp helper · level 1 · ran · our draft was wrong · ea57468fd987573b
  5. build_backbone helper · level 0 · unverified · d4f09015805919e2
  6. build_decoder helper · level 1 · ran · our draft was wrong · 6d2d9f8f46a73fc3
  7. build_sr_decoder helper · level 1 · ran · our draft was wrong · 6d5672a93099e8b5
  8. _SynchronizedBatchNorm helper · level 1 · ran · 9f557ce8389a603f
  9. ASPP model · level 0 · unverified · fced7a51f0af7316
  10. Decoder model · level 0 · unverified · 69e2ae26d39d9541
  11. SyncMaster helper · level 1 · ran · 93f1be24e0653bc8
  12. _sum_ft helper · level 1 · ran · violated contract · 3151cee68a1020dc
  13. _unsqueeze_ft helper · level 1 · ran · honoured contract · 1efd43bcf31727c0
  14. _ASPPModule helper · level 0 · unverified · 5e90ce39dc46a1c4
  15. FutureResult helper · level 1 · ran · 9e8c636cac1d847f
  16. SlavePipe helper · level 1 · ran · e75aa93b78286d50
  1. deeplabv3 · dfd957d2101652d7 · 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. DeepLab · eedd50d5d3810673 · 14 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. DeepLabV3Plus · f4c9e20cce9d961b · 17 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. ASPP · f758f80fd2d75c17 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. RoadSegmentation · fc74ea4c65f40986 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. ASPP · ffacfdf35eef3a55 · 9 bricks; individually on a fixture: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1802.02611") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderImage ClassificationImage SegmentationLesion SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) DeepLab v3+ Dice 0.4609 #3 of 5 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) DeepLab v3+ IoU 0.3458 #3 of 5 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) DeepLab v3+ Precision 0.5831 #3 of 5 Archive leaderboard report
Semantic Segmentation AI-TOD DeepLabV3+(ResNet-50) Dice 43.52 #2 of 2 Archive leaderboard report
Semantic Segmentation BDD100K val Deeplabv3+ mIoU 63.6 #4 of 24 Archive leaderboard report
Semantic Segmentation BJRoad DeepLabv3+ IoU 50.81 #11 of 11 Archive leaderboard report
Semantic Segmentation Cityscapes val DeepLabv3+ (Dilated-Xception-71) mIoU 79.6 #57 of 99 Archive leaderboard report
Semantic Segmentation DADA-seg DeepLabV3+ (ACDC) mIoU 26.8 #12 of 28 Archive leaderboard report
Semantic Segmentation DensePASS DeepLabV3+ (ResNet-101) mIoU 32.5% #21 of 36 Archive leaderboard report
Semantic Segmentation EventScape DeepLabV3+ mIoU 53.65 #6 of 12 Archive leaderboard report
Semantic Segmentation Fine-Grained Grass Segmentation Dataset DeepLabv3+ mIoU 47.95 #7 of 10 Archive leaderboard report
Semantic Segmentation MCubeS DeepLabV3+ (RGB-A-D-N) mIoU 38.13% #20 of 22 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test DeepLabv3+ (Xception-65-JFT) Mean IoU 89.0% #1 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test DeepLabv3+ (Xception-JFT) Mean IoU 89.0% #2 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val DeepLabV3+ (ResNet-101) mIoU (Syn) 75.39 #29 of 29 Archive leaderboard report
Semantic Segmentation Potsdam DeepLabV3+ mIoU 83.67 #3 of 3 Archive leaderboard report
Semantic Segmentation SkyScapes-Dense DeepLabv3+ Mean IoU 38.20 #2 of 7 Archive leaderboard report
Semantic Segmentation SynPASS DeepLabv3+ mIoU 29.66% #5 of 6 Archive leaderboard report
Semantic Segmentation Trans10K DeepLabV3+ GFLOPs 37.98 #5 of 15 Archive leaderboard report
Semantic Segmentation Trans10K DeepLabV3+ mIoU 68.87% #5 of 15 Archive leaderboard report
Semantic Segmentation US3D DeepLabV3+ mIoU 74.42 #1 of 3 Archive leaderboard report
Semantic Segmentation UrbanLF DeepLabV3+ (ResNet-101) mIoU (Real) 76.27 #14 of 14 Archive leaderboard report
Semantic Segmentation Vaihingen DeepLabV3+ mIoU 72.90 #13 of 13 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 ConvolutionASPPAverage PoolingBatch NormalizationConvolutionDeepLabv3Dense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDilated ConvolutionGlobal Average PoolingMax PoolingPointwise ConvolutionPyramid Pooling ModuleReLUResidual ConnectionSoftmaxSpatial Pyramid Pooling

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