Papers › DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,...

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

2 Jun 2016arXiv:1606.00915archive 2025-07-28

Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7% mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

PaperPDFCodeCode 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

Syntology 63 code samples harvested from 16 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 63 samples from 16 repositories, 43 ran (35 with no instrument failure; 8 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 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 43 samples that ran has no recorded date.

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

DeepMotionAIResearch/DenseASPP mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
Lxrd-AJ/Advanced_ML mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
NASA-NeMO-Net/NeMO-Net mentioned on GitHubtfSyntology: not harvested report
OIdiotLin/DeepLab-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Popcorn-sugar/Deep_v2 mentioned on GitHubtfSyntology: not harvested report
Qengineering/TensorFlow-Lite-RPi-32-bit-Segmentation mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
Qengineering/TensorFlow-Lite-RPi-64-bit-Segmentation mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
Qengineering/TensorFlow_Lite_Segmentation_Jetson-Nano mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
Qengineering/TensorFlow_Lite_Segmentation_RPi_32-bit mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
Qengineering/TensorFlow_Lite_Segmentation_RPi_64-bit mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
RituYadav92/Image-segmentation mentioned on GitHubpytorchSyntology: not harvested report
ShichengChen/WaveUNet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
aldo-aguilar/nu-style mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
cdmh/deeplab-public-ver2 mentioned on GitHubNOASSERTIONSyntology: not harvested report
cgsaxner/UB_Segmentation mentioned on GitHubtfMITSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
divisionai/deep-photo-styletransfer mentioned on GitHubtorchSyntology: not harvested report
eceo-epfl/scaleprotoseg mentioned on GitHubpytorchMITSyntology: 12 samples, 12 ran (4 instrument-failed) · 0 unverified report
halbielee/EPS mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
isht7/pytorch-deeplab-resnet mentioned on GitHubpytorchMITSyntology: not harvested report
johnnylu305/Simple-does-it-weakly-supervised-instance-and-semantic-segmentation mentioned on GitHubtfApache-2.0Syntology: not harvested report
johnnylu305/deeplab-imagenet-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-Stuff: Thing and Stuff Classes in Context (arXiv:1612.03716; that paper's own run record: 8 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; 1 where Syntology's instrument failed) · 21 unverified); nothing checks that they implement this paper's method. report
johnsun03/myTest mentioned on GitHubtorchSyntology: not harvested report
kazuto1011/deeplab-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-Stuff: Thing and Stuff Classes in Context (arXiv:1612.03716; that paper's own run record: 8 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; 1 where Syntology's instrument failed) · 21 unverified); nothing checks that they implement this paper's method. report
kdethoor/panoptictorch mentioned on GitHubpytorchSyntology: not harvested report
keb123keb/deeplabv2 mentioned on GitHubSyntology: not harvested report
leimao/DeepLab-V3 mentioned on GitHubtfSyntology: 5 samples, 0 ran · 5 unverified report
leimao/DeepLab_v3 mentioned on GitHubtfSyntology: not harvested report
liarba/caffe_dev mentioned on GitHubNOASSERTIONSyntology: not harvested report
open-cv/deeplab-v2 mentioned on GitHubNOASSERTIONSyntology: not harvested report
purushothamgowthu/deep-photo-styletransfer mentioned on GitHubtorchSyntology: not harvested report
stevendleung/w251-project-door-camera-public mentioned on GitHubpytorchSyntology: not harvested report
switchablenorms/SwitchNorm_Segmentation mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
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
violin0847/crowdcounting mentioned on GitHubSyntology: not harvested report
waggle-sensor/plugin-water-detector mentioned on GitHubpytorchSyntology: not harvested report
wangleihitcs/DeepLab-V1-PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
warmspringwinds/pytorch-segmentation-detection mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
woonhahaha/place-classification mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-Stuff: Thing and Stuff Classes in Context (arXiv:1612.03716; that paper's own run record: 8 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; 1 where Syntology's instrument failed) · 21 unverified); nothing checks that they implement this paper's method. report
yaq007/Autofocus-Layer mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
z01nl1o02/deeplab-v2 mentioned on GitHubNOASSERTIONSyntology: not harvested report
zej-luffy/deeplab-public-ver2 mentioned on GitHubNOASSERTIONSyntology: not harvested report
zllrunning/deeplab-pytorch-crf mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
Daeijavad/Deeplab-CRF tfSyntology: 1 sample, 0 ran · 1 unverified report
Media-Smart/vedaseg pytorchSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified 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
Shun14/deeplab-paddle paddleSyntology: not harvested 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

63 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
34ran
20unverified

Licence: 18 of the 63 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 16 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.

DeepMotionAIResearch/DenseASPP community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
_Transition models/DenseASPP.py ran no licence file found · pointer only · 6dc18b4169cafab5 · report fixture: returned _Transition · level recorded 2026-09-22
DenseASPP models/DenseASPP.py unverified no licence file found · pointer only · 8a58f32a65726f57 · report
_DenseAsppBlock models/DenseASPP.py unverified no licence file found · pointer only · 6a76699fca4b02b5 · report
_DenseBlock models/DenseASPP.py unverified no licence file found · pointer only · e62f57b4d5854c77 · report
_DenseLayer models/DenseASPP.py unverified no licence file found · pointer only · a1a737ad0daed701 · report
Lxrd-AJ/Advanced_ML community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
UNet in 40 papers Implementation/unet_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · eb36d73a1d6a9211 · report fixture: returned UNet · level recorded 2026-09-22
UNetConv2D Implementation/unet_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 964a4d471b87d037 · report fixture: returned UNetConv2D · level recorded 2026-09-22
UNetUpConv2D Implementation/unet_model.py ran no licence file found · pointer only · 311989e0cef13762 · report fixture: signature inputs1:Tensor/4/float, inputs2:Tensor/4/float · returned Tensor · level recorded 2026-09-24
OIdiotLin/DeepLab-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
ASPPModule src/networks/deeplabv3.py unverified no licence file found · pointer only · 3edb28451c5d5ab9 · report
ShichengChen/WaveUNet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ASPP_module pytorch-pyrmaid/networks/deeplab_xception.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 88e7802a88d1a1f9 · report fixture: returned ASPP_module · level recorded 2026-09-22
aldo-aguilar/nu-style community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
get_input_optimizer src/handlers.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8f043783be05520d · report fixture: signature input_img:Tensor/4/float · returned LBFGS · level recorded 2026-09-22
image_loader in 17 papers src/dataset.py ran MIT (permissive) · c70da0d4921fa08b · report fixture: signature image_name:str/0/str, imsize:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-26
getData in 7 papers CycleGan/src/dataset.py unverified MIT (permissive) · 1127bbe82e43e0e6 · report
get_style_model_and_loss src/handlers.py unverified MIT (permissive) · 8ead0bc727213153 · report
cgsaxner/UB_Segmentation community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
bilinear_upsampling_weights upsampling.py ran MIT (permissive) · d241a51429ebbb55 · report fixture: signature factor:int/0/int, num_channels:int/0/int · returned ndarray · level recorded 2026-09-26
iou_coeff metrics.py ran MIT (permissive) · dd2ff9a3c0d64a92 · report fixture: signature label:SymbolicTensor/4/float, prediction:SymbolicTensor/4/float · returned EagerTensor · level recorded 2026-09-26
read_and_decode in 5 papers tf_records.py unverified MIT (permissive) · 3ec5c6029a21dcbb · report
tnr metrics.py unverified MIT (permissive) · 5f3a2a92473d303a · report
tpr metrics.py unverified MIT (permissive) · e903f992c748c9e3 · report
eceo-epfl/scaleprotoseg community (archive-listed) 12 samples, 12 ran (4 instrument-failed) · 0 unverified
compute_layer_rf_info receptive_field.py ran MIT (permissive) · c2f4bd843f1e0e47 · report fixture: signature layer_filter_size:int/0/int, layer_stride:int/0/int, layer_padding:str/0/str, previous_layer_rf_info:list/1/int · returned list · level recorded 2026-09-25
compute_rf_protoL_at_spatial_location receptive_field.py ran MIT (permissive) · efb66ddd03d907f4 · report fixture: signature img_height:int/0/int, img_width:int/0/int, height_index:int/0/int, width_index:int/0/int, protoL_rf_info:list/1/int · returned list · level recorded 2026-09-26
compute_rf_prototype receptive_field.py ran MIT (permissive) · efea10148e03ffc4 · report fixture: signature img_size:int/0/int, prototype_patch_index:tuple/1/int, protoL_rf_info:tuple/1/int · returned list · level recorded 2026-09-26
create_logger in 172 papers log.py ran MIT (permissive) · da0f80d54b852951 · report fixture: signature log_filename:str/0/str, display:bool/0/bool · returned tuple · level recorded 2026-09-26
find_continuous_high_activation_crop helpers.py ran MIT (permissive) · 159cfd7b77ad44a5 · report fixture: signature activation_map:ndarray/2/float, patch_bbox:tuple/1/int, threshold:float/0/float, add_margin:int/0/int · returned tuple · level recorded 2026-09-26
find_high_activation_crop helpers.py ran MIT (permissive) · a578552e64b8de7e · report fixture: signature activation_map:ndarray/2/float, percentile:int/0/int · returned tuple · level recorded 2026-09-26
get_lr in 91 papers segmentation/em/module_em.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 7337f1f5ff01dcd0 · report fixture: signature optimizer:SGD/0/? · returned float · level recorded, date not recorded
list_of_distances helpers.py ran · our draft was wrong fingerprinted MIT (permissive) · c9e92d0b7ff929fe · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float · returned Tensor · level recorded 2026-09-26
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
preprocess.py ran · our draft was wrong fingerprinted MIT (permissive) · 2f5c8689a7884f62 · report fixture: signature x:Tensor/4/float, mean:tuple/1/float, std:tuple/1/float · returned Tensor · level recorded 2026-09-26
preprocess_input_function preprocess.py ran · our draft was wrong fingerprinted MIT (permissive) · d22fdfbc49113693 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-26
sanitize_config_val_for_json segmentation/config.py ran MIT (permissive) · 32401bdce2879798 · report fixture: signature val:dict/0/? · returned dict · level recorded 2026-09-26
undo_preprocess in 5 papers preprocess.py ran · our draft was wrong fingerprinted MIT (permissive) · efb86a8611f14f72 · report fixture: signature x:Tensor/4/float, mean:tuple/1/float, std:tuple/1/float · returned Tensor · level recorded 2026-09-26
halbielee/EPS community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Net in 54 papers network/resnet38d.py ran fingerprinted no licence file found · pointer only · 09eb18c5d7d60dfc · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Normalize in 154 papers network/resnet38d.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · bb0ad51ace15dbe4 · report fixture: signature img:ndarray/3/int · returned ndarray · 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 this sample: bucket 2 of 2, arg 1: rank 4, kind float, dtype float32
network/resnet38d.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c844437a798458b7 · report fixture: signature x:Tensor/4/float, get_x_bn_relu:bool/0/bool · returned Tensor · level recorded 2026-09-22
ResBlock_bot network/resnet38d.py ran · metamorphic tier: invariant no licence file found · pointer only · 282223ddd3ff3f7c · report fixture: signature x:Tensor/4/float, get_x_bn_relu:bool/0/bool · returned Tensor · level recorded 2026-09-22
leimao/DeepLab-V3 community (archive-listed) 5 samples, 0 ran · 5 unverified
DeepLab model.py unverified MIT (permissive) · ac381b8ad8a845a3 · report
MobileNet in 6 papers model.py unverified MIT (permissive) · 9a312354c4aac598 · report
Resnet in 6 papers model.py unverified MIT (permissive) · 59f29ececcd49f37 · report
Vgg16 model.py unverified MIT (permissive) · 0682c73df452506f · report
atrous_spatial_pyramid_pooling model.py unverified MIT (permissive) · c8a45bd65a5b3b97 · report
switchablenorms/SwitchNorm_Segmentation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ResnetDilated models/models.py ran fingerprinted no licence file found · pointer only · d8bef07c9adf425e · report fixture: returned ResnetDilated · level recorded 2026-09-22
wangleihitcs/DeepLab-V1-PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VGG16_LargeFOV nets/vgg.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 85fce95aedb122ac · report fixture: returned VGG16_LargeFOV · level recorded 2026-09-22
warmspringwinds/pytorch-segmentation-detection community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
ASPP in 23 papers pytorch_segmentation_detection/models/deeplab.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 53f17388b003b9b6 · report fixture: returned ASPP · level recorded 2026-09-22
conv3x3 in 1,376 papers pytorch_segmentation_detection/models/deeplab.py ran · our draft was wrong MIT (permissive) · 9e2edfa6c37815a7 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
yaq007/Autofocus-Layer community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
ASPP_c models.py ran MIT (permissive) · 6dc0febe733fd5b9 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
models.py ran · metamorphic tier: invariant MIT (permissive) · 44f2f26a9ed8d32f · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
zllrunning/deeplab-pytorch-crf community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
DeepLabV2 libs/models/deeplabv2.py ran fingerprinted MIT (permissive) · 5d9bd49de1275265 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
_ASPPModule in 7 papers libs/models/deeplabv2.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 3d1880c02d075eba · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_Bottleneck libs/models/deeplabv2.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 84e049f7b9fa13b7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_ConvBatchNormReLU libs/models/deeplabv2.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 6cd27134d67d87a8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_ResBlock libs/models/deeplabv2.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · ae539753ae4d52c4 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Daeijavad/Deeplab-CRF community (archive-listed) 1 sample, 0 ran · 1 unverified
Network in 40 papers network_class.py unverified no licence file found · pointer only · f1deead3b623ea55 · report
Media-Smart/vedaseg community (archive-listed) 11 samples, 7 ran (2 instrument-failed) · 4 unverified
ASPPConv in 9 papers vedaseg/models/encoders/enhance_modules/aspp.py ran fingerprinted Apache-2.0 (permissive) · 308ccdb3fbb740d8 · report fixture: returned ASPPConv · level recorded 2026-09-22
ASPPPooling in 6 papers vedaseg/models/encoders/enhance_modules/aspp.py ran fingerprinted Apache-2.0 (permissive) · 1ded95feb039492a · report fixture: returned ASPPPooling · level recorded 2026-09-22
FRN vedaseg/models/encoders/enhance_modules/aspp.py ran Apache-2.0 (permissive) · 116bb1dc1ccdde04 · report fixture: returned FRN · level recorded 2026-09-22
Registry in 34 papers vedaseg/models/encoders/enhance_modules/aspp.py ran Apache-2.0 (permissive) · d18cf36c9276960f · report fixture: returned Registry · level recorded 2026-09-22
TLU vedaseg/models/encoders/enhance_modules/aspp.py ran Apache-2.0 (permissive) · 82583067173f244a · report fixture: returned TLU · level recorded 2026-09-22
build_act_layer in 8 papers vedaseg/models/encoders/enhance_modules/aspp.py ran · our draft was wrong Apache-2.0 (permissive) · 0f5c1cdac6542626 · report fixture: signature cfg:dict/0/?, num_features:int/0/int, postfix:str/0/str, layer_only:bool/0/bool · returned tuple · level recorded 2026-09-22
build_norm_layer in 14 papers vedaseg/models/encoders/enhance_modules/aspp.py ran · our draft was wrong Apache-2.0 (permissive) · fcbdd0b7fa92032b · report fixture: signature cfg:dict/0/?, num_features:int/0/int, postfix:str/0/str, layer_only:bool/0/bool · returned tuple · level recorded 2026-09-22
ASPP in 23 papers vedaseg/models/encoders/enhance_modules/aspp.py unverified Apache-2.0 (permissive) · 8a6aac3339ee8802 · report
constant_init in 10 papers vedaseg/models/encoders/enhance_modules/aspp.py unverified Apache-2.0 (permissive) · 5ceabf20d794e5bd · report
init_weights in 109 papers vedaseg/models/encoders/enhance_modules/aspp.py unverified Apache-2.0 (permissive) · 20164401c294879a · report
kaiming_init in 9 papers vedaseg/models/encoders/enhance_modules/aspp.py unverified Apache-2.0 (permissive) · 17876e40add6c703 · report

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.

12 assemblies on this paper: 12 harvested, 0 generated, listed in 2 groups (siblings lifted in one batch form one group).

6 sibling assemblies for DeepLab (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for DeepLab (graph method: DeepLab). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. VGG16_LargeFOV entry · level 1 · ran · 85fce95aedb122ac

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

one of 6 siblings

  1. Network entry · level 0 · unverified · f1deead3b623ea55

harvested Assembly for DeepLab (graph method: DeepLab). 5 bricks; individually on a fixture: 0 ran · 5 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. DeepLab entry · level 0 · unverified · ac381b8ad8a845a3
  2. MobileNet helper · level 0 · unverified · 9a312354c4aac598
  3. Resnet helper · level 0 · unverified · 59f29ececcd49f37
  4. Vgg16 helper · level 0 · unverified · 0682c73df452506f
  5. atrous_spatial_pyramid_pooling helper · level 0 · unverified · c8a45bd65a5b3b97

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

one of 6 siblings

  1. UNet entry · level 1 · ran · eb36d73a1d6a9211
  2. UNetConv2D helper · level 1 · ran · 964a4d471b87d037
  3. UNetUpConv2D helper · level 1 · ran · 311989e0cef13762

harvested Assembly for DeepLab (graph method: DeepLab). 4 bricks; individually on a fixture: 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) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. Net entry · level 1 · ran · 09eb18c5d7d60dfc
  2. Normalize helper · level 1 · ran · bb0ad51ace15dbe4
  3. ResBlock model · level 1 · ran · c844437a798458b7
  4. ResBlock_bot model · level 1 · ran · 282223ddd3ff3f7c

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

one of 6 siblings

  1. DeepLabV2 entry · level 1 · ran · 5d9bd49de1275265
  2. _ASPPModule model · level 1 · ran · 3d1880c02d075eba
  3. _ConvBatchNormReLU helper · level 1 · ran · 6cd27134d67d87a8
  4. _ResBlock helper · level 1 · ran · ae539753ae4d52c4
  5. _Bottleneck helper · level 1 · ran · 84e049f7b9fa13b7

6 sibling assemblies for atrous spatial pyramid pooling (ASPP) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for atrous spatial pyramid pooling (ASPP) (graph method: atrous spatial pyramid pooling (ASPP)). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. ASPP entry · level 1 · ran · 53f17388b003b9b6
  2. conv3x3 helper · level 1 · ran · our draft was wrong · 9e2edfa6c37815a7

harvested Assembly for atrous spatial pyramid pooling (ASPP) (graph method: atrous spatial pyramid pooling (ASPP)). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. ASPP_module entry · level 1 · ran · 88e7802a88d1a1f9

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

one of 6 siblings

  1. ASPPModule entry · level 0 · unverified · 3edb28451c5d5ab9

harvested Assembly for atrous spatial pyramid pooling (ASPP) (graph method: atrous spatial pyramid pooling (ASPP)). 11 bricks; individually on a fixture: 7 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. ASPP entry · level 0 · unverified · 8a6aac3339ee8802
  2. ASPPConv model · level 1 · ran · 308ccdb3fbb740d8
  3. ASPPPooling model · level 1 · ran · 1ded95feb039492a
  4. build_act_layer helper · level 1 · ran · our draft was wrong · 0f5c1cdac6542626
  5. build_norm_layer helper · level 1 · ran · our draft was wrong · fcbdd0b7fa92032b
  6. init_weights helper · level 0 · unverified · 20164401c294879a
  7. constant_init helper · level 0 · unverified · 5ceabf20d794e5bd
  8. kaiming_init helper · level 0 · unverified · 17876e40add6c703
  9. FRN helper · level 1 · ran · 116bb1dc1ccdde04
  10. Registry helper · level 1 · ran · d18cf36c9276960f
  11. TLU helper · level 1 · ran · 82583067173f244a

harvested Assembly for atrous spatial pyramid pooling (ASPP) (graph method: atrous spatial pyramid pooling (ASPP)). 5 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 4 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. DenseASPP entry · level 0 · unverified · 8a58f32a65726f57
  2. _DenseAsppBlock model · level 0 · unverified · 6a76699fca4b02b5
  3. _DenseBlock model · level 0 · unverified · e62f57b4d5854c77
  4. _Transition helper · level 1 · ran · 6dc18b4169cafab5
  5. _DenseLayer model · level 0 · unverified · a1a737ad0daed701

harvested Assembly for atrous spatial pyramid pooling (ASPP) (graph method: atrous spatial pyramid pooling (ASPP)). 2 bricks; individually on a fixture: 2 ran (of which 0 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) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. ASPP_c entry · level 1 · ran · 6dc0febe733fd5b9
  2. BasicBlock helper · level 1 · ran · 44f2f26a9ed8d32f

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="1606.00915") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test DeepLab-CRF (ResNet-101) Mean IoU (class) 70.4% #82 of 105 Archive leaderboard report
Semantic Segmentation Event-based Segmentation Dataset DeepLab mIoU 71.05 #4 of 6 Archive leaderboard report
Semantic Segmentation PASCAL Context DeepLabV2 mIoU 45.7 #55 of 66 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test DeepLab-CRF (ResNet-101) Mean IoU 79.7% #31 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val DeepLab-CRF (ResNet-101) mIoU 77.69% #15 of 29 Archive leaderboard report
Semantic Segmentation SELMA DeepLabV2 mIoU 68.9 #4 of 7 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: ASPP, DeepLabv2

1x1 ConvolutionASPPAverage PoolingBatch NormalizationBottleneck Residual BlockCRFConvolutionDCNNDeepLabv2Dense ConnectionsDilated ConvolutionDropoutFeedforward NetworkGlobal Average PoolingKaiming InitializationMax PoolingPolynomial Rate DecayRandom ScalingReLUResidual BlockResidual ConnectionSGD with MomentumSoftmaxSpatial Pyramid PoolingWeight 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