Papers › Topology-Aware Uncertainty for Image Segmentation

Topology-Aware Uncertainty for Image Segmentation

9 Jun 2023NeurIPS 2023 11arXiv:2306.05671archive 2025-07-28

Saumya Gupta, Yikai Zhang, Xiaoling Hu, Prateek Prasanna, Chao Chen

Segmentation of curvilinear structures such as vasculature and road networks is challenging due to relatively weak signals and complex geometry/topology. To facilitate and accelerate large scale annotation, one has to adopt semi-automatic approaches such as proofreading by experts. In this work, we focus on uncertainty estimation for such tasks, so that highly uncertain, and thus error-prone structures can be identified for human annotators to verify. Unlike most existing works, which provide pixel-wise uncertainty maps, we stipulate it is crucial to estimate uncertainty in the units of topological structures, e.g., small pieces of connections and branches. To achieve this, we leverage tools from topological data analysis, specifically discrete Morse theory (DMT), to first capture the structures, and then reason about their uncertainties. To model the uncertainty, we (1) propose a joint prediction model that estimates the uncertainty of a structure while taking the neighboring structures into consideration (inter-structural uncertainty); (2) propose a novel Probabilistic DMT to model the inherent uncertainty within each structure (intra-structural uncertainty) by sampling its representations via a perturb-and-walk scheme. On various 2D and 3D datasets, our method produces better structure-wise uncertainty maps compared to existing works. Code available at https://github.com/Saumya-Gupta-26/struct-uncertainty

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

Syntology 27 code samples harvested from 5 repositories linked to this paper: 21 ran (of which 4 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 25 samples from 4 repositories, 20 ran (17 with no instrument failure; 3 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.

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 21 samples that ran has no recorded date.

Saumya-Gupta-26/struct-uncertainty officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 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.

Code Syntology ran Syntology

27 samples harvested: 21 ran (of which 4 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 6 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.

3ran · our draft was wrong
1ran; the contract check could not run
17ran
6unverified

Licence: 7 of the 27 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 5 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 3 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 2, 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; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

Saumya-Gupta-26/struct-uncertainty official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
parse_func infer.py ran · our draft was wrong no licence file found · pointer only · d30fa705b8e23cb4 · report fixture: signature args:Namespace/0/? · returned tuple · level recorded, date not recorded
DMT dmt_2d.py unverified no licence file found · pointer only · e63919c931ba1e99 · report
johschmidt42/PyTorch-2D-3D-UNet-Tutorial found in paper text by Syntology 9 samples, 8 ran (2 instrument-failed) · 1 unverified
autocrop in 6 papers unet.py ran; the contract check could not run (RAISES) MIT (permissive) · b128f04e610e22c8 · report fixture: returned tuple · level recorded 2026-09-22
create_dense_target transformations.py ran fingerprinted MIT (permissive) · 7f1458886e91abd9 · report fixture: signature tar:ndarray/1/int · returned ndarray · level recorded 2026-09-26
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
losses.py ran MIT (permissive) · 291fdb8dff7cf15e · report fixture: signature probs:Tensor/4/float, target:Tensor/4/float, weight:float/0/float, eps:float/0/float, smooth:float/0/float · returned Tensor · level recorded 2026-09-26
get_conv_layer in 7 papers unet.py ran · our draft was wrong MIT (permissive) · 53bab7232f605d02 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, bias:bool/0/bool, dim:int/0/int · returned Conv2d · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
transformations.py ran fingerprinted MIT (permissive) · ab7d4eaddf5ca7e9 · report fixture: signature inp:ndarray/2/float, mean:float/0/float, std:float/0/float · returned ndarray · level recorded 2026-09-26
normalize_01 transformations.py ran fingerprinted MIT (permissive) · a207a2db9756ef69 · report fixture: signature inp:ndarray/2/float · returned ndarray · level recorded 2026-09-26
plot_training visual.py ran MIT (permissive) · 66aa286caeb3283b · report fixture: signature training_losses:ndarray/1/float, validation_losses:ndarray/1/float, learning_rate:ndarray/1/float, gaussian:bool/0/bool, sigma:int/0/int, figsize:tuple/1/int · returned Figure · level recorded 2026-09-26
predict in 126 papers inference.py ran MIT (permissive) · 02c8d4823f0bd036 · report fixture: signature img:ndarray/2/float, model:callable/0/?, preprocess:callable/0/?, postprocess:callable/0/?, device:str/0/str · returned ndarray · level recorded 2026-09-26
conv_layer in 44 papers unet.py unverified MIT (permissive) · c78cf3e9f814160b · report
gigantenbein/UNet-Zoo found in paper text by Syntology 2 samples, 2 ran (0 instrument-failed) · 0 unverified
increase_resolution models/phiseg3D.py ran Apache-2.0 (permissive) · 497d8b92031530bc · report fixture: signature times:int/0/int, input_dim:int/0/int, output_dim:int/0/int · returned Sequential · level recorded 2026-09-26
load_data_into_loader load_LIDC_data.py ran Apache-2.0 (permissive) · 4463af1a7a2f90d4 · report fixture: returned tuple · level recorded 2026-09-26
HuXiaoling/Structural_Uncertainty found in paper text by Syntology 5 samples, 2 ran (0 instrument-failed) · 3 unverified
AxisAlignedConvGaussian probabilistic_unet.py ran no licence file found · pointer only · c163bba7de076605 · report fixture: signature input:Tensor/4/float, segm:NoneType/0/? · returned tuple · level recorded 2026-09-24
Encoder in 278 papers probabilistic_unet.py ran fingerprinted no licence file found · pointer only · 0326380a477a365f · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ProbabilisticUnet probabilistic_unet.py unverified no licence file found · pointer only · 260ed13140183edd · report
UNet in 40 papers probabilistic_unet.py unverified no licence file found · pointer only · 477da3a4420e7316 · report
init_weights in 109 papers probabilistic_unet.py unverified no licence file found · pointer only · f0e750b2fb39dd62 · report
iMED-Lab/CS-Net found in paper text by Syntology 9 samples, 8 ran (1 instrument-failed) · 1 unverified
AffinityAttention model/csnet.py ran · metamorphic tier: deterministic MIT (permissive) · 605dbaeb7a17d95a · report fixture: returned AffinityAttention · level recorded 2026-09-22
CSNet model/csnet.py ran · metamorphic tier: deterministic MIT (permissive) · efdf1f54291e5b38 · report fixture: returned CSNet · level recorded 2026-09-22
ChannelAttentionBlock model/csnet.py ran fingerprinted MIT (permissive) · 5b2a9f8699891fa8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Decoder in 210 papers model/csnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · b5b8a23ced0e8669 · report fixture: returned Decoder · level recorded 2026-09-22
ResEncoder model/csnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ea12770312446fcc · report fixture: returned ResEncoder · level recorded 2026-09-22
SpatialAttentionBlock model/csnet.py ran MIT (permissive) · c96bc45ac6dfcbdf · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
deconv in 48 papers model/csnet.py ran · our draft was wrong MIT (permissive) · b528298ef3ced2c0 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
downsample in 59 papers model/csnet.py ran · metamorphic tier: deterministic MIT (permissive) · a7606e101556581b · report fixture: returned MaxPool2d · level recorded 2026-09-22
initialize_weights in 30 papers model/csnet.py unverified MIT (permissive) · fe857ca50126df0e · 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Probabilistic DMT (graph method: Probabilistic DMT). 9 bricks; individually on a fixture: 8 ran (of which 4 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) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. CSNet entry · level 1 · ran · efdf1f54291e5b38
  2. AffinityAttention model · level 1 · ran · 605dbaeb7a17d95a
  3. Decoder model · level 1 · ran · b5b8a23ced0e8669
  4. ResEncoder model · level 1 · ran · ea12770312446fcc
  5. deconv helper · level 1 · ran · our draft was wrong · b528298ef3ced2c0
  6. downsample helper · level 1 · ran · a7606e101556581b
  7. initialize_weights helper · level 0 · unverified · fe857ca50126df0e
  8. ChannelAttentionBlock model · level 1 · ran · 5b2a9f8699891fa8
  9. SpatialAttentionBlock model · level 1 · ran · c96bc45ac6dfcbdf

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

one of 3 siblings

  1. DMT entry · level 0 · unverified · e63919c931ba1e99

harvested Assembly for Probabilistic DMT (graph method: Probabilistic DMT). 6 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) · 4 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ProbabilisticUnet entry · level 0 · unverified · 260ed13140183edd
  2. AxisAlignedConvGaussian model · level 1 · ran · c163bba7de076605
  3. UNet helper · level 0 · unverified · 477da3a4420e7316
  4. Encoder model · level 1 · ran · 0326380a477a365f
  5. init_weights helper · level 0 · unverified · f0e750b2fb39dd62
  6. truncated_normal_ helper · level 0 · unverified · 6f12908079fae859

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="2306.05671") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image SegmentationSegmentationSemantic SegmentationTopological Data Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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