Papers › Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling

Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling

26 Jul 2023CVPR 2023 1arXiv:2307.14126archive 2025-07-28

Hu Wang, Yuanhong Chen, Congbo Ma, Jodie Avery, Louise Hull, Gustavo Carneiro

The missing modality issue is critical but non-trivial to be solved by multi-modal models. Current methods aiming to handle the missing modality problem in multi-modal tasks, either deal with missing modalities only during evaluation or train separate models to handle specific missing modality settings. In addition, these models are designed for specific tasks, so for example, classification models are not easily adapted to segmentation tasks and vice versa. In this paper, we propose the Shared-Specific Feature Modelling (ShaSpec) method that is considerably simpler and more effective than competing approaches that address the issues above. ShaSpec is designed to take advantage of all available input modalities during training and evaluation by learning shared and specific features to better represent the input data. This is achieved from a strategy that relies on auxiliary tasks based on distribution alignment and domain classification, in addition to a residual feature fusion procedure. Also, the design simplicity of ShaSpec enables its easy adaptation to multiple tasks, such as classification and segmentation. Experiments are conducted on both medical image segmentation and computer vision classification, with results indicating that ShaSpec outperforms competing methods by a large margin. For instance, on BraTS2018, ShaSpec improves the SOTA by more than 3% for enhancing tumour, 5% for tumour core and 3% for whole tumour. The code repository address is https://github.com/billhhh/ShaSpec/.

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 21 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (6 with no instrument failure; 5 where Syntology's instrument failed); found in paper text by Syntology: 7 samples from 1 repository, 2 ran (2 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

billhhh/ShaSpec officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 11 ran (5 instrument-failed) · 3 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

21 samples harvested: 13 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 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
2ran; the contract check could not run
8ran
8unverified

Licence: 21 of the 21 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 2 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”. “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.

billhhh/ShaSpec official repository 14 samples, 11 ran (5 instrument-failed) · 3 unverified
ASPP in 23 papers DualNet_SS.py ran · metamorphic tier: deterministic no licence file found · pointer only · f11a6e90cadb7f4a · report fixture: returned ASPP · level recorded 2026-09-22
Activation_layer DualNet_SS.py ran · our draft was wrong no licence file found · pointer only · 87a835e5bb115092 · report fixture: signature activation_cfg:str/0/str, inplace:bool/0/bool · returned ReLU · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
DualNet_SS.py ran no licence file found · pointer only · aecac45f39b0b8d7 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
Bottleneck in 98 papers DualNet_SS.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3c153f25c25aaeb4 · report fixture: returned Bottleneck · level recorded 2026-09-22
CompositionalLayer DualNet_SS.py ran · metamorphic tier: deterministic no licence file found · pointer only · 487b6da3a3ee0baf · report fixture: returned CompositionalLayer · level recorded 2026-09-22
Conv3d_wd DualNet_SS.py ran · metamorphic tier: deterministic no licence file found · pointer only · f87647971702596d · report fixture: returned Conv3d_wd · level recorded 2026-09-22
Norm_layer DualNet_SS.py ran · our draft was wrong no licence file found · pointer only · 6c8ddf5a387fa62b · report fixture: signature norm_cfg:str/0/str, inplanes:int/0/int · returned BatchNorm3d · level recorded 2026-09-22
U_Res3D_dec DualNet_SS.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7bbb9eb9394c1277 · report fixture: returned U_Res3D_dec · level recorded 2026-09-22
conv3x3x3 in 32 papers DualNet_SS.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · ab85f0066b239697 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:tuple/1/int, stride:tuple/1/int, padding:tuple/1/int, dilation:tuple/1/int, groups:int/0/int, bias:bool/0/bool, weight_std:bool/0/bool · returned Conv3d_wd · level recorded 2026-09-22
downsample_basic_block in 26 papers DualNet_SS.py ran · our draft was wrong no licence file found · pointer only · 285c8c634525802b · report fixture: returned Tensor · level recorded 2026-09-22
plot_embedding_2D DualNet_SS.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 976c8ef5d66a359c · report fixture: signature data:ndarray/2/float, label:list/1/int, colors:ndarray/1/float, title:str/0/str · returned Figure · level recorded 2026-09-22
DualNet_SS DualNet_SS.py unverified no licence file found · pointer only · feb64926fe058ff2 · report
ResNet in 139 papers DualNet_SS.py unverified no licence file found · pointer only · c193cbe2e1e98ec6 · report
U_Res3D_enc DualNet_SS.py unverified no licence file found · pointer only · f871bd06635f4139 · report
cchen-cc/Robust-Mseg found in paper text by Syntology 7 samples, 2 ran (0 instrument-failed) · 5 unverified
decode_images in 5 papers utils.py ran no licence file found · pointer only · 43fa9247f4e0be35 · report fixture: signature imgs:ndarray/5/float, num_images:int/0/int · returned ndarray · level recorded 2026-09-24
kl_loss in 37 papers
census: 8 implementations from 11 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
losses.py ran no licence file found · pointer only · db52c4f2bee05325 · report fixture: signature mu:EagerTensor/2/float, logvar:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
decode_labels utils.py unverified no licence file found · pointer only · ab241f8602321aab · report
dice_eval stats_func.py unverified no licence file found · pointer only · eebe5a9b8acdd970 · report
generator in 11 papers modalitydrop_generator.py unverified no licence file found · pointer only · cc57c3ca7844ba89 · report
load_data in 700 papers data_loader.py unverified no licence file found · pointer only · 69ee388442ee2275 · report
task_loss losses.py unverified no licence file found · pointer only · 6620889b2afcdb57 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Shared-Specific Feature Modelling (ShaSpec) (graph method: Shared-Specific Feature Modelling (ShaSpec)). 14 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. DualNet_SS entry · level 0 · unverified · feb64926fe058ff2
  2. CompositionalLayer model · level 1 · ran · 487b6da3a3ee0baf
  3. U_Res3D_dec model · level 1 · ran · 7bbb9eb9394c1277
  4. U_Res3D_enc model · level 0 · unverified · f871bd06635f4139
  5. plot_embedding_2D helper · level 1 · ran; the contract check could not run (RAISES) · 976c8ef5d66a359c
  6. conv3x3x3 helper · level 1 · ran; the contract check could not run (RAISES) · ab85f0066b239697
  7. Activation_layer helper · level 1 · ran · our draft was wrong · 87a835e5bb115092
  8. BasicBlock helper · level 1 · ran · aecac45f39b0b8d7
  9. Conv3d_wd helper · level 1 · ran · f87647971702596d
  10. Norm_layer helper · level 1 · ran · our draft was wrong · 6c8ddf5a387fa62b
  11. ASPP helper · level 1 · ran · f11a6e90cadb7f4a
  12. ResNet helper · level 0 · unverified · c193cbe2e1e98ec6
  13. Bottleneck helper · level 1 · ran · 3c153f25c25aaeb4
  14. downsample_basic_block helper · level 1 · ran · our draft was wrong · 285c8c634525802b

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="2307.14126") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClassificationImage SegmentationMedical Image SegmentationSegmentationSemantic Segmentationdomain classification

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