Papers › Lightweight Probabilistic Deep Networks

Lightweight Probabilistic Deep Networks

29 May 2018CVPR 2018 6arXiv:1805.11327archive 2025-07-28

Jochen Gast, Stefan Roth

Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simple networks. The size of the inputs and the depth of typical CNN architectures in computer vision only compound this problem. Uncertainty in neural networks has thus been largely ignored in practice, despite the fact that it may provide important information about the reliability of predictions and the inner workings of the network. In this paper, we introduce two lightweight approaches to making supervised learning with probabilistic deep networks practical: First, we suggest probabilistic output layers for classification and regression that require only minimal changes to existing networks. Second, we employ assumed density filtering and show that activation uncertainties can be propagated in a practical fashion through the entire network, again with minor changes. Both probabilistic networks retain the predictive power of the deterministic counterpart, but yield uncertainties that correlate well with the empirical error induced by their predictions. Moreover, the robustness to adversarial examples is significantly increased.

PaperPDFConference PDFCodeCode 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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 1 repository, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 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. 1 of the 10 samples that ran has no recorded date.

cdebeunne/uncertainties_CNN mentioned on GitHubpytorchSyntology: not harvested report
marcoancona/dasp mentioned on GitHubtfSyntology: not harvested report
mattiasegu/uncertainty_estimation_deep_learning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A General Framework for Uncertainty Estimation in Deep Learning (arXiv:1907.06890; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
uzh-rpg/deep_uncertainty_estimation mentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (1 instrument-failed) · 2 unverified 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

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 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.

1ran · our draft was wrong
9ran
2unverified

Licence: 2 of the 12 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 uzh-rpg/deep_uncertainty_estimation. “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.

uzh-rpg/deep_uncertainty_estimation community (archive-listed) 12 samples, 10 ran (1 instrument-failed) · 2 unverified
ResNet18Dropout models/resnet_dropout.py ran MIT (permissive) · 74375051502358ff · report fixture: signature p:float/0/float · returned ResNetDropout · level recorded 2026-09-25
ResNet34Dropout models/resnet_dropout.py ran MIT (permissive) · 1884001022ae28e1 · report fixture: signature p:float/0/float · returned ResNetDropout · level recorded 2026-09-25
ResNet50Dropout models/resnet_dropout.py ran MIT (permissive) · 2d425fd536a399c7 · report fixture: signature p:float/0/float · returned ResNetDropout · level recorded 2026-09-25
format_time in 140 papers utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 8d7ec010c29e813b · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
get_mean_and_std in 55 papers utils.py ran · metamorphic tier: well formed MIT (permissive) here; the stored copy is pointer only · 3cbdd3b190b16350 · report fixture: signature dataset:MinimalDataset/0/? · returned tuple · level recorded 2026-09-22
keep_variance models_adf/resnet_adf.py ran fingerprinted MIT (permissive) · f61dfa3535aa5a2c · report fixture: signature x:Tensor/2/float, min_variance:float/0/float · returned Tensor · level recorded 2026-09-25
normcdf contrib/math.py ran fingerprinted MIT (permissive) · 41dcab2b71a44f78 · report fixture: signature value:Tensor/2/float, mu:float/0/float, stddev:float/0/float · returned Tensor · level recorded 2026-09-25
normpdf in 5 papers contrib/math.py ran fingerprinted MIT (permissive) · 60464d053ab983d9 · report fixture: signature value:Tensor/2/float, mu:float/0/float, stddev:float/0/float · returned Tensor · level recorded 2026-09-25
resize2D contrib/interpolation.py ran MIT (permissive) · 8cfc523838a908cb · report fixture: signature inputs:Tensor/4/float, size_targets:list/1/int, mode:str/0/str · returned Tensor · level recorded 2026-09-25
resize2D_as contrib/interpolation.py ran MIT (permissive) · 0c731e06a7a2bd80 · report fixture: signature inputs:Tensor/4/float, output_as:Tensor/4/float, mode:str/0/str · returned Tensor · level recorded 2026-09-25
lbeta contrib/lgamma_function/lgamma_function.py unverified MIT (permissive) · bc27551e10c4c57c · report
lgamma contrib/lgamma_function/lgamma_function.py unverified MIT (permissive) · 7c11ba3bece5471a · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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