Papers › Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures...

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

9 Nov 2015arXiv:1511.02680archive 2025-07-28

Alex Kendall, Vijay Badrinarayanan, Roberto Cipolla

We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making. Our contribution is a practical system which is able to predict pixel-wise class labels with a measure of model uncertainty. We achieve this by Monte Carlo sampling with dropout at test time to generate a posterior distribution of pixel class labels. In addition, we show that modelling uncertainty improves segmentation performance by 2-3% across a number of state of the art architectures such as SegNet, FCN and Dilation Network, with no additional parametrisation. We also observe a significant improvement in performance for smaller datasets where modelling uncertainty is more effective. We benchmark Bayesian SegNet on the indoor SUN Scene Understanding and outdoor CamVid driving scenes datasets.

PaperPDFCodeCode Syntology ran

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 18 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 18 samples from 1 repository, 6 ran (6 with no instrument failure; 0 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 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

Fangrn/caffe-segnet mentioned on GitHubNOASSERTIONSyntology: not harvested report
Paultool/segnet mentioned on GitHubNOASSERTIONSyntology: not harvested report
SkyWa7ch3r/ImageSegmentation mentioned on GitHubtfSyntology: not harvested report
SkyWa7ch3r/SceneSegmentation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 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); nothing checks that they implement this paper's method. report
TimoSaemann/caffe-segnet-cudnn5 mentioned on GitHubNOASSERTIONSyntology: not harvested report
TqDavid/td mentioned on GitHubNOASSERTIONSyntology: not harvested report
Zhanghongbin-github/SegNet-Tutorial mentioned on GitHubcaffe2Syntology: not harvested report
alexgkendall/SegNet-Tutorial mentioned on GitHubcaffe2Syntology: not harvested report
alexgkendall/caffe-segnet mentioned on GitHubNOASSERTIONSyntology: not harvested report
azy64/Deep-Learning mentioned on GitHubtfSyntology: not harvested report
billlyzhaoyh/SegNetFromScratch mentioned on GitHubtfSyntology: not harvested report
hmi88/what mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (arXiv:1703.04977; that paper's own run record: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
hoidn/ptychopinn mentioned on GitHubtfGPL-3.0Syntology: not harvested report
hosshonarvar/Image-Segmentation mentioned on GitHubtfMITSyntology: 18 samples, 6 ran (0 instrument-failed) · 12 unverified report
janisgp/Sampling-free-Epistemic-Uncertainty mentioned on GitHubtfSyntology: not harvested report
mrmtn86/python1 mentioned on GitHubcaffe2Syntology: not harvested report
navganti/SIVO mentioned on GitHubGPL-3.0Syntology: not harvested report
navganti/SegNet mentioned on GitHubcaffe2Syntology: not harvested report
nshaud/DeepNetsForEO mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yubaoliu/caffe-segnet mentioned on GitHubNOASSERTIONSyntology: not harvested report
zhucheng725/MobileNetv1_Segnet_keras_tensorrt mentioned on GitHubtfSyntology: 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

18 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 12 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.

6ran
12unverified

Licence: 0 of the 18 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 hosshonarvar/Image-Segmentation. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

hosshonarvar/Image-Segmentation community (archive-listed) 18 samples, 6 ran (0 instrument-failed) · 12 unverified
conv2d_layer my_code/Src/operations.py ran MIT (permissive) · 1100155deac6df9c · report fixture: signature input_layer:EagerTensor/4/float, name:str/0/str, weights_layer:EagerTensor/4/float, biases_layer:EagerTensor/1/float, train_flag:EagerTensor/0/bool · returned EagerTensor · level recorded 2026-09-26
decoder_parameters_layer my_code/Src/parameters.py ran MIT (permissive) · 08141afc1fd47d42 · report fixture: signature filters_layers:dict/0/?, parameters_layers:dict/0/? · returned dict · level recorded 2026-09-26
get_filename_list others_code/inputs_object.py ran MIT (permissive) · bac4ea89c9097ba1 · report fixture: signature path:str/0/str, config:dict/0/? · returned tuple · level recorded 2026-09-26
initialize_parameters_layer my_code/Src/parameters.py ran fingerprinted MIT (permissive) · 1176233b38437ed1 · report fixture: signature num_classes:int/0/int · returned dict · level recorded 2026-09-26
maxpool2d_indices_layer my_code/Src/operations.py ran MIT (permissive) · 2ef0bbabe4e8a662 · report fixture: signature input_layer:EagerTensor/4/float · returned tuple · level recorded 2026-09-26
read_paths_file my_code/Src/input.py ran MIT (permissive) · d79699ab9dd285c3 · report fixture: signature paths_file:str/0/str · returned tuple · level recorded 2026-09-26
batch_norm in 46 papers others_code/layers_object.py unverified MIT (permissive) · 5d5ab2d2e269268e · report
cal_loss in 20 papers others_code/evaluation_object.py unverified MIT (permissive) · 00a137eeb688bbf2 · report
conv_layer in 44 papers others_code/layers_object.py unverified MIT (permissive) · da64ac3ea0aa102b · report
create_dataset in 47 papers my_code/Src/input.py unverified MIT (permissive) · 28e9700e3cfdeda0 · report
dataset_inputs others_code/inputs_object.py unverified MIT (permissive) · b64e374d9b820bbd · report
dataset_reader others_code/inputs_object.py unverified MIT (permissive) · 8d70ecc459a5e844 · report
get_parameters in 30 papers my_code/Src/parameters.py unverified MIT (permissive) · 6b793951869a5684 · report
max_pool in 11 papers others_code/layers_object.py unverified MIT (permissive) · f72cdb6c9c2d1060 · report
normal_loss in 6 papers others_code/evaluation_object.py unverified MIT (permissive) · 2185e76397ed29f7 · report
parse_dataset in 8 papers my_code/Src/input.py unverified MIT (permissive) · 465a1df98fcaa53d · report
upsample2d_layer my_code/Src/operations.py unverified MIT (permissive) · 0a684097c5925075 · report
weighted_loss in 53 papers others_code/evaluation_object.py unverified MIT (permissive) · 2dee72e12c7f0a5d · report

Tasks

Decision MakingDecoderLow-Light Image EnhancementScene UnderstandingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationConvolutionDropoutKaiming InitializationMax PoolingReLUSegNetSoftmax

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