Papers › 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

21 Jun 2016arXiv:1606.06650archive 2025-07-28

Özgün Çiçek, Ahmed Abdulkadir, Soeren S. Lienkamp, Thomas Brox, Olaf Ronneberger

This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.

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 76 code samples harvested from 13 repositories linked to this paper: 59 ran (of which 18 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 0 violated, 38 with no contract checked; 17 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 76 samples from 13 repositories, 59 ran (42 with no instrument failure; 17 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 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.

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

AghdamAmir/3D-UNet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Iammuratc/grainDetection mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
Shrajan/AAAI-2022 mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
Shrajan/IB_U_Nets mentioned on GitHubpytorchSyntology: not harvested report
UdonDa/3D-UNet-PyTorch mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (3 instrument-failed) · 1 unverified report
VernicaJ/Volumetric-Segmentation mentioned on GitHubSyntology: not harvested report
aschethor/Teaching_Incompressible_Fluid_Dynamics_to_3D_CNNs mentioned on GitHubpytorchSyntology: not harvested report
black0017/MedicalZooPytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation (arXiv:1606.04797; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified) and HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation (arXiv:1804.02967; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
chenyizi086/wu.2023.sigspatial mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (4 instrument-failed) · 0 unverified report
edraizen/molmimic mentioned on GitHubpytorchSyntology: not harvested report
elektronn/elektronn3 mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report
fepegar/unet mentioned on GitHubpytorchSyntology: 12 samples, 8 ran (5 instrument-failed) · 4 unverified report
gvtulder/elasticdeform mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
jamiljami/Unet mentioned on GitHubSyntology: not harvested report
kilgore92/PyTorch-UNet mentioned on GitHubpytorchMITSyntology: not harvested report
leohsuofnthu/Pytorch-IterativeFCN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
lyqcom/3d-unet mentioned on GitHubmindsporeApache-2.0Syntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
manideep03/Brain-Tumor-Segmentation mentioned on GitHubMITSyntology: not harvested report
mlf-core/liver-ct-segmentation mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
qsyao/cuda_spatial_deform mentioned on GitHubSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
wolny/pytorch-3dunet mentioned on GitHubpytorchSyntology: 19 samples, 13 ran (1 instrument-failed) · 6 unverified report
2023-MindSpore-1/ms-code-53 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-7 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code3 mindsporeSyntology: not harvested report
ZhouZhang233/SCU-MindSpore-UNnet3D-project mindsporeSyntology: not harvested report
jiajun169/mindspore_models mindsporeApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
yangyucheng000/MSpaper mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Supervision Can Be a Good Few-Shot Learner (arXiv:2207.09176; that paper's own run record: 5 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; 3 where Syntology's instrument failed) · 5 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

76 samples harvested: 59 ran (of which 18 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 0 violated, 38 with no contract checked; 17 where Syntology's instrument failed) · 17 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.

4ran · honoured contract
13ran · our draft was wrong
4ran; the contract check could not run
38ran
17unverified

Licence: 20 of the 76 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 13 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 5 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.

AghdamAmir/3D-UNet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Conv3DBlock unet3d.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 961a837607030f03 · report fixture: signature input:Tensor/5/float · returned tuple · level recorded 2026-09-22
UNet3D unet3d.py ran · metamorphic tier: invariant no licence file found · pointer only · 35a374cce6fae706 · report fixture: signature input:Tensor/5/float · returned Tensor · level recorded 2026-09-22
UpConv3DBlock unet3d.py ran · metamorphic tier: invariant no licence file found · pointer only · fc75937f18b2d1a0 · report fixture: signature input:Tensor/5/float, residual:Tensor/5/float · returned Tensor · level recorded 2026-09-22
Iammuratc/grainDetection community (archive-listed) 1 sample, 0 ran · 1 unverified
unet3D model.py unverified no licence file found · pointer only · e96116a2cbef22f9 · report
Shrajan/AAAI-2022 community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Bottom networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · bd5f5829c2ce4f4a · report fixture: returned Bottom · level recorded 2026-09-22
Conv3x3 in 6 papers networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 002f393823c7b57c · report fixture: returned Conv3x3 · level recorded 2026-09-22
Decoder in 210 papers networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 92c21f0cfe8583db · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · c1d32ca647fc4e21 · report fixture: returned Encoder · level recorded 2026-09-22
TConv networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · f9811d05b5c818c0 · report fixture: returned TConv · level recorded 2026-09-22
UNet in 40 papers networks/unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5d0be67e9ea65011 · report fixture: returned UNet · level recorded 2026-09-22
UdonDa/3D-UNet-PyTorch community (archive-listed) 5 samples, 4 ran (3 instrument-failed) · 1 unverified
conv_block_2_3d src/model.py ran · our draft was wrong MIT (permissive) · 769628dc3a9af468 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int, activation:callable/0/? · returned Sequential · level recorded 2026-09-22
conv_block_3d src/model.py ran · our draft was wrong MIT (permissive) · 520950cb24a9041a · report fixture: signature in_dim:int/0/int, out_dim:int/0/int, activation:callable/0/? · returned Sequential · level recorded 2026-09-22
conv_trans_block_3d src/model.py ran · our draft was wrong MIT (permissive) · 74e9ef01fdad6274 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int, activation:callable/0/? · returned Sequential · level recorded 2026-09-22
max_pooling_3d src/model.py ran MIT (permissive) · a5b542b783b2f9c1 · report fixture: returned MaxPool3d · level recorded 2026-09-24
UNet in 40 papers src/model.py unverified MIT (permissive) · 08a841012a2f2d6c · report
chenyizi086/wu.2023.sigspatial community (archive-listed) 5 samples, 5 ran (4 instrument-failed) · 0 unverified
UNet3D model/unet3d/unet3d.py ran no licence file found · pointer only · a23aa4c62d2ced83 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
center_in model/unet3d/unet3d.py ran · our draft was wrong no licence file found · pointer only · 6322564404e6ac5b · report fixture: signature in_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-22
center_out model/unet3d/unet3d.py ran · our draft was wrong no licence file found · pointer only · 00e223e69984d6d2 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-22
conv_block in 95 papers model/unet3d/unet3d.py ran · our draft was wrong no licence file found · pointer only · aaac350375676434 · report fixture: signature in_dim:int/0/int, middle_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-22
up_conv_block model/unet3d/unet3d.py ran · our draft was wrong no licence file found · pointer only · 38e1ecb8f675c611 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-22
elektronn/elektronn3 community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
DownConv in 9 papers elektronn3/models/unet.py ran fingerprinted MIT (permissive) · 4fbc8e441e25d534 · report fixture: signature x:Tensor/5/float · returned tuple · level recorded 2026-09-24
GridAttention elektronn3/models/unet.py ran fingerprinted MIT (permissive) · 74dfc4e293ff8a68 · report fixture: signature x:Tensor/5/float, g:Tensor/5/float · returned tuple · level recorded 2026-09-24
get_conv in 21 papers elektronn3/models/unet.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · d473e9bce385040b · report fixture: signature dim:int/0/int · returned type · level recorded 2026-09-22
get_convtranspose in 5 papers elektronn3/models/unet.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · a3169a7b1435e0dc · report fixture: signature dim:int/0/int · returned type · level recorded 2026-09-22
get_maxpool in 5 papers elektronn3/models/unet.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · a12e2f04ad60d321 · report fixture: signature dim:int/0/int · returned type · level recorded 2026-09-22
UNet in 40 papers elektronn3/models/unet.py unverified MIT (permissive) · 7a32dce4d065a404 · report
UpConv in 9 papers elektronn3/models/unet.py unverified MIT (permissive) · 54df8e2e39fdda93 · report
fepegar/unet community (archive-listed) 12 samples, 8 ran (5 instrument-failed) · 4 unverified
ConvolutionalBlock unet/unet.py ran fingerprinted MIT (permissive) · 7bc5f5b5c8b2e7be · report fixture: returned ConvolutionalBlock · level recorded 2026-09-22
DecodingBlock unet/unet.py ran MIT (permissive) · 44f8060512ddb75c · report fixture: returned DecodingBlock · level recorded 2026-09-22
EncodingBlock unet/unet.py ran fingerprinted MIT (permissive) · d10aff0e169c4244 · report fixture: returned EncodingBlock · level recorded 2026-09-22
fix_upsampling_type unet/unet.py ran · our draft was wrong fingerprinted MIT (permissive) · 48a77a4b4c6899cd · report fixture: signature upsampling_type:str/0/str, dimensions:int/0/int · returned str · level recorded 2026-09-22
get_conv_transpose_layer unet/unet.py ran · our draft was wrong MIT (permissive) · ea1e09fb045807d8 · report fixture: signature dimensions:int/0/int, in_channels:int/0/int, out_channels:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
get_downsampling_layer unet/unet.py ran · our draft was wrong MIT (permissive) · abe939ebcfbefc61 · report fixture: signature dimensions:int/0/int, pooling_type:str/0/str, kernel_size:int/0/int · returned MaxPool2d · level recorded 2026-09-22
get_upsampling_layer unet/unet.py ran · our draft was wrong MIT (permissive) · 29992fbf80f8c0a1 · report fixture: signature upsampling_type:str/0/str · returned Upsample · level recorded 2026-09-22
run in 143 papers tests/test_unet.py ran · our draft was wrong MIT (permissive) · 12ba822b7c231300 · report fixture: signature model:callable/0/?, shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
Decoder in 210 papers unet/unet.py unverified MIT (permissive) · 0e22a90528c239e0 · report
Encoder in 278 papers unet/unet.py unverified MIT (permissive) · 8254969b26258f52 · report
UNet in 40 papers unet/unet.py unverified MIT (permissive) · 6103d27eb89d2193 · report
UNet3D unet/unet.py unverified MIT (permissive) · e25b932cbe95a18e · report
leohsuofnthu/Pytorch-IterativeFCN community (archive-listed) 1 sample, 0 ran · 1 unverified
IterativeFCN iterativeFCN.py unverified no licence file found · pointer only · a1d5172c411b098d · report
lyqcom/3d-unet community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
first in 17 papers src/utils.py ran Apache-2.0 (permissive) · 42ad2df596a897dd · report fixture: signature iterable:list/1/int, default:NoneType/0/? · returned int · level recorded 2026-09-26
get_random_patch src/utils.py ran Apache-2.0 (permissive) · 47769d97406c079f · report fixture: signature dims:tuple/1/int, patch_size:tuple/1/int, rand_fn:NoneType/0/? · returned tuple · level recorded 2026-09-26
correct_nifti_head src/utils.py unverified Apache-2.0 (permissive) · 6e413b6f8321f25a · report
mlf-core/liver-ct-segmentation community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
liver_ct_segmentation/model/unet_3d_models.py ran · metamorphic tier: invariant MIT (permissive) · 86cf127000aad21a · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
DownSamplingBlock liver_ct_segmentation/model/unet_3d_models.py ran MIT (permissive) · 84be777da492a5a6 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
InputBlock liver_ct_segmentation/model/unet_3d_models.py ran · metamorphic tier: invariant MIT (permissive) · d7c2338ecaef5f6f · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
OutputBlock liver_ct_segmentation/model/unet_3d_models.py ran · metamorphic tier: invariant MIT (permissive) · fdd735c8d5934a67 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
UpSamplingBlock liver_ct_segmentation/model/unet_3d_models.py ran · metamorphic tier: invariant MIT (permissive) · 723045ebfbbe3377 · report fixture: signature x1:Tensor/5/float, x2:Tensor/5/float · returned Tensor · level recorded 2026-09-22
UNet3D liver_ct_segmentation/model/unet_3d_models.py unverified MIT (permissive) · 21dc7d3844afe540 · report
qsyao/cuda_spatial_deform community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
bool_to_int cuda_backend/py_api.py ran · honoured contract fingerprinted licence not identified · pointer only · 3ae04df8b3a499d0 · report fixture: signature flag:bool/0/bool · returned int · level recorded 2026-09-22
create_matrix_rotation_x_3d deform.py ran · honoured contract licence not identified · pointer only · aea00ce54798f811 · report fixture: signature angle:float/0/float, matrix:NoneType/0/? · returned ndarray · level recorded 2026-09-22
create_zero_centered_coordinate_mesh deform.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence not identified · pointer only · fdaa4b7e9a216060 · report fixture: signature shape:tuple/1/int · returned ndarray · level recorded 2026-09-22
scale_coords deform.py ran · honoured contract fingerprinted licence not identified · pointer only · a7d7bc408835cb44 · report fixture: signature coords:Tensor/2/float, scale:Tensor/0/float · returned Tensor · level recorded 2026-09-22
wolny/pytorch-3dunet community (archive-listed) 19 samples, 13 ran (1 instrument-failed) · 6 unverified
AbstractUpsampling pytorch3dunet/unet3d/model.py ran fingerprinted MIT (permissive) · bd5255830dbc70df · report fixture: returned AbstractUpsampling · level recorded 2026-09-22
ChannelSELayer3D pytorch3dunet/unet3d/model.py ran MIT (permissive) · d8c51afcfab2dccb · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
ChannelSpatialSELayer3D pytorch3dunet/unet3d/model.py ran MIT (permissive) · e48fc3ac38e078bb · report fixture: returned ChannelSpatialSELayer3D · level recorded 2026-09-22
InterpolateUpsampling pytorch3dunet/unet3d/model.py ran fingerprinted MIT (permissive) · 5312c997daffbe4f · report fixture: returned InterpolateUpsampling · level recorded 2026-09-22
NoUpsampling pytorch3dunet/unet3d/model.py ran fingerprinted MIT (permissive) · b71250ad47097e99 · report fixture: returned NoUpsampling · level recorded 2026-09-22
ResNetBlock in 8 papers pytorch3dunet/unet3d/model.py ran MIT (permissive) · e2c1fc74b0aa7fc6 · report fixture: returned ResNetBlock · level recorded 2026-09-22
ResNetBlockSE pytorch3dunet/unet3d/model.py ran MIT (permissive) · fba2e5652d7a6ce1 · report fixture: returned ResNetBlockSE · level recorded 2026-09-22
SingleConv pytorch3dunet/unet3d/model.py ran MIT (permissive) · 26f42cb5865457f1 · report fixture: returned SingleConv · level recorded 2026-09-22
SpatialSELayer3D pytorch3dunet/unet3d/model.py ran MIT (permissive) · 0ae1c43a043456ae · report fixture: signature x:Tensor/5/float, weights:NoneType/0/? · returned Tensor · level recorded 2026-09-24
TransposeConvUpsampling pytorch3dunet/unet3d/model.py ran MIT (permissive) · cb3c64452fa192f4 · report fixture: returned TransposeConvUpsampling · level recorded 2026-09-22
UNet3D pytorch3dunet/unet3d/model.py ran MIT (permissive) · c59e8b03c790e76b · report fixture: returned UNet3D · level recorded 2026-09-22
create_conv in 7 papers pytorch3dunet/unet3d/model.py ran · our draft was wrong MIT (permissive) · d0ca7c4c392589d5 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, order:str/0/str, num_groups:int/0/int, padding:int/0/int, dropout_prob:float/0/float, is3d:bool/0/bool · returned list · level recorded 2026-09-22
number_of_features_per_level pytorch3dunet/unet3d/model.py ran · honoured contract fingerprinted MIT (permissive) · 9c4cd085f7952fa0 · report fixture: signature init_channel_number:int/0/int, num_levels:int/0/int · returned list · level recorded 2026-09-22
AbstractUNet pytorch3dunet/unet3d/model.py unverified MIT (permissive) · d98c95b8fc1ede43 · report
Decoder in 210 papers pytorch3dunet/unet3d/model.py unverified MIT (permissive) · d6b608560176497b · report
Encoder in 278 papers pytorch3dunet/unet3d/model.py unverified MIT (permissive) · d42847dc9240c8d5 · report
create_decoders pytorch3dunet/unet3d/model.py unverified MIT (permissive) · 1682295cd0093044 · report
create_encoders pytorch3dunet/unet3d/model.py unverified MIT (permissive) · 27fd44d28f16c5a5 · report
jiajun169/mindspore_models community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
a_cosine_learning_rate in 5 papers Unet3d/src/lr_schedule.py ran Apache-2.0 (permissive) · 316fb42e9e6ed79e · report fixture: signature current_step:int/0/int, base_lr:float/0/float, warmup_steps:int/0/int, decay_steps:int/0/int · returned float · level recorded 2026-09-24
dynamic_lr in 7 papers Unet3d/src/lr_schedule.py ran Apache-2.0 (permissive) · 90a0e8705a358db8 · report fixture: signature config:Config/0/?, base_step:int/0/int · returned list · level recorded 2026-09-26
get_list_of_files_in_dir Unet3d/src/convert_nifti.py ran Apache-2.0 (permissive) · 77063b815fa723a0 · report fixture: signature directory:str/0/str, file_types:str/0/str · returned list · level recorded 2026-09-26
linear_warmup_learning_rate in 8 papers Unet3d/src/lr_schedule.py ran fingerprinted Apache-2.0 (permissive) · d6a99ec714147ac1 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24

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.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 6 bricks; individually on a fixture: 6 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet entry · level 1 · ran · 5d0be67e9ea65011
  2. Bottom model · level 1 · ran · bd5f5829c2ce4f4a
  3. Decoder model · level 1 · ran · 92c21f0cfe8583db
  4. Encoder model · level 1 · ran · c1d32ca647fc4e21
  5. Conv3x3 helper · level 1 · ran · 002f393823c7b57c
  6. TConv helper · level 1 · ran · f9811d05b5c818c0

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. unet3D entry · level 0 · unverified · e96116a2cbef22f9

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 11 bricks; individually on a fixture: 7 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; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet3D entry · level 0 · unverified · e25b932cbe95a18e
  2. UNet helper · level 0 · unverified · 6103d27eb89d2193
  3. ConvolutionalBlock model · level 1 · ran · 7bc5f5b5c8b2e7be
  4. Decoder model · level 0 · unverified · 0e22a90528c239e0
  5. Encoder model · level 0 · unverified · 8254969b26258f52
  6. EncodingBlock model · level 1 · ran · d10aff0e169c4244
  7. DecodingBlock model · level 1 · ran · 44f8060512ddb75c
  8. fix_upsampling_type helper · level 1 · ran · our draft was wrong · 48a77a4b4c6899cd
  9. get_downsampling_layer helper · level 1 · ran · our draft was wrong · abe939ebcfbefc61
  10. get_conv_transpose_layer helper · level 1 · ran · our draft was wrong · ea1e09fb045807d8
  11. get_upsampling_layer helper · level 1 · ran · our draft was wrong · 29992fbf80f8c0a1

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 19 bricks; individually on a fixture: 13 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet3D entry · level 1 · ran · c59e8b03c790e76b
  2. AbstractUNet helper · level 0 · unverified · d98c95b8fc1ede43
  3. DoubleConv model · level 0 · unverified · 00cd22c3bcba8bf8
  4. create_decoders helper · level 0 · unverified · 1682295cd0093044
  5. create_encoders helper · level 0 · unverified · 27fd44d28f16c5a5
  6. number_of_features_per_level helper · level 1 · ran · honoured contract · 9c4cd085f7952fa0
  7. SingleConv helper · level 1 · ran · 26f42cb5865457f1
  8. Decoder model · level 0 · unverified · d6b608560176497b
  9. Encoder model · level 0 · unverified · d42847dc9240c8d5
  10. create_conv helper · level 1 · ran · our draft was wrong · d0ca7c4c392589d5
  11. InterpolateUpsampling helper · level 1 · ran · 5312c997daffbe4f
  12. NoUpsampling helper · level 1 · ran · b71250ad47097e99
  13. ResNetBlock helper · level 1 · ran · e2c1fc74b0aa7fc6
  14. ResNetBlockSE helper · level 1 · ran · fba2e5652d7a6ce1
  15. TransposeConvUpsampling helper · level 1 · ran · cb3c64452fa192f4
  16. AbstractUpsampling helper · level 1 · ran · bd5255830dbc70df
  17. ChannelSELayer3D helper · level 1 · ran · d8c51afcfab2dccb
  18. ChannelSpatialSELayer3D helper · level 1 · ran · e48fc3ac38e078bb
  19. SpatialSELayer3D helper · level 1 · ran · 0ae1c43a043456ae

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 6 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) · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet3D entry · level 0 · unverified · 21dc7d3844afe540
  2. ConvBlock helper · level 1 · ran · 86cf127000aad21a
  3. DownSamplingBlock helper · level 1 · ran · 84be777da492a5a6
  4. InputBlock helper · level 1 · ran · d7c2338ecaef5f6f
  5. OutputBlock helper · level 1 · ran · fdd735c8d5934a67
  6. UpSamplingBlock helper · level 1 · ran · 723045ebfbbe3377

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 5 bricks; individually on a fixture: 5 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; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet3D entry · level 1 · ran · a23aa4c62d2ced83
  2. center_in model · level 1 · ran · our draft was wrong · 6322564404e6ac5b
  3. center_out model · level 1 · ran · our draft was wrong · 00e223e69984d6d2
  4. conv_block model · level 1 · ran · our draft was wrong · aaac350375676434
  5. up_conv_block model · level 1 · ran · our draft was wrong · 38e1ecb8f675c611

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 17 bricks; individually on a fixture: 15 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet entry · level 0 · unverified · 7a32dce4d065a404
  2. DownConv model · level 1 · ran · 4fbc8e441e25d534
  3. GridAttention helper · level 1 · ran · 74dfc4e293ff8a68
  4. UpConv model · level 0 · unverified · 54df8e2e39fdda93
  5. conv1 helper · level 1 · ran · our draft was wrong · ca6e9ccb83b4a75f
  6. conv3 model · level 1 · ran · our draft was wrong · 856a6341a797b42d
  7. get_activation helper · level 1 · ran · our draft was wrong · 689e68cf031b9f81
  8. get_maxpool helper · level 1 · ran; the contract check could not run (RAISES) · a12e2f04ad60d321
  9. get_normalization helper · level 1 · ran · our draft was wrong · e90f1b8757aa4598
  10. planar_kernel helper · level 1 · ran · honoured contract · 8b9d5abd0d40fd51
  11. DummyAttention helper · level 1 · ran · 436c9c4a56f1ac76
  12. autocrop helper · level 1 · ran · violated contract · 5f8c8ad9bcc1103e
  13. upconv2 model · level 1 · ran · our draft was wrong · 441b10347086c3f9
  14. get_conv helper · level 1 · ran; the contract check could not run (RAISES) · d473e9bce385040b
  15. planar_pad helper · level 1 · ran · honoured contract · 86acb4c08221afdd
  16. ResizeConv helper · level 1 · ran · 5e50e483df5d6165
  17. get_convtranspose helper · level 1 · ran; the contract check could not run (RAISES) · a3169a7b1435e0dc

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 3 bricks; individually on a fixture: 3 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet3D entry · level 1 · ran · 35a374cce6fae706
  2. Conv3DBlock model · level 1 · ran · 961a837607030f03
  3. UpConv3DBlock model · level 1 · ran · fc75937f18b2d1a0

harvested Assembly for 3D U-Net (graph method: 3D U-Net). 5 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. UNet entry · level 0 · unverified · 08a841012a2f2d6c
  2. conv_block_2_3d helper · level 1 · ran · our draft was wrong · 769628dc3a9af468
  3. conv_block_3d helper · level 1 · ran · our draft was wrong · 520950cb24a9041a
  4. conv_trans_block_3d helper · level 1 · ran · our draft was wrong · 74e9ef01fdad6274
  5. max_pooling_3d helper · level 1 · ran · a5b542b783b2f9c1

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="1606.06650") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Instance SegmentationData AugmentationMachine TranslationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation ScanNet(v2) UNet-Backbone mAP @ 50 31.9 #29 of 32 Archive leaderboard report
3D Part Segmentation ShapeNet-Part 3D-UNet [Cicek:2016un] Instance Average IoU 84.6 #60 of 67 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

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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