Papers › EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation

EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation

11 May 2024CVPR 2024 1arXiv:2405.06880archive 2025-07-28

Md Mostafijur Rahman, Mustafa Munir, Radu Marculescu

An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficiency. EMCAD leverages a unique multi-scale depth-wise convolution block, significantly enhancing feature maps through multi-scale convolutions. EMCAD also employs channel, spatial, and grouped (large-kernel) gated attention mechanisms, which are highly effective at capturing intricate spatial relationships while focusing on salient regions. By employing group and depth-wise convolution, EMCAD is very efficient and scales well (e.g., only 1.91M parameters and 0.381G FLOPs are needed when using a standard encoder). Our rigorous evaluations across 12 datasets that belong to six medical image segmentation tasks reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively. Moreover, EMCAD's adaptability to different encoders and versatility across segmentation tasks further establish EMCAD as a promising tool, advancing the field towards more efficient and accurate medical image analysis. Our implementation is available at https://github.com/SLDGroup/EMCAD.

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 23 code samples harvested from 1 repository linked to this paper: 20 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 7 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: 23 samples from 1 repository, 20 ran (12 with no instrument failure; 8 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. 1 of the 20 samples that ran has no recorded date.

sldgroup/emcad officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 23 samples, 20 ran (8 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

23 samples harvested: 20 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
1ran; the contract check could not run
10ran
3unverified

Licence: 23 of the 23 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 sldgroup/emcad. “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 4 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.

sldgroup/emcad official repository 23 samples, 20 ran (8 instrument-failed) · 3 unverified
CAB in 6 papers lib/decoders.py ran fingerprinted licence not identified · pointer only · 936d2bcb208f34c4 · report fixture: returned CAB · level recorded 2026-09-22
EUCB lib/decoders.py ran fingerprinted licence not identified · pointer only · 74c35cc1eda22a07 · report fixture: returned EUCB · level recorded 2026-09-22
LGAG lib/decoders.py ran licence not identified · pointer only · c6413739abe9afc8 · report fixture: returned LGAG · level recorded 2026-09-22
MSCB lib/decoders.py ran fingerprinted licence not identified · pointer only · 9d62846b5a3faf10 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MSDC lib/decoders.py ran fingerprinted licence not identified · pointer only · 099a7b3762fb1d23 · report fixture: returned MSDC · level recorded 2026-09-22
SAB in 5 papers lib/decoders.py ran fingerprinted licence not identified · pointer only · 1afc66cfd19166c9 · report fixture: returned SAB · level recorded 2026-09-22
act_layer in 20 papers lib/decoders.py ran · our draft was wrong licence not identified · pointer only · bb51501828a7b35a · report fixture: signature act:str/0/str, inplace:bool/0/bool, neg_slope:float/0/float, n_prelu:int/0/int · returned ReLU · level recorded 2026-09-22
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
lib/decoders.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b9da06d4f527dd6c · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22
conv3x3 in 1,376 papers lib/resnet.py ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
data_split in 17 papers utils/format_conversion.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 8cbe68372aad40f6 · report fixture: signature src_list:list/1/int · returned list · level recorded 2026-09-24
dice_coefficient in 17 papers train_polyp.py ran · our draft was wrong fingerprinted licence not identified · pointer only · b0f51daf2afa7ccb · report fixture: signature predicted:Tensor/2/float, labels:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gcd lib/decoders.py ran · honoured contract fingerprinted licence not identified · pointer only · a6fad4bca9a84fcf · report fixture: signature a:int/0/int, b:int/0/int · returned int · level recorded 2026-09-22
get_loader in 62 papers utils/dataloader.py ran licence not identified · pointer only · fc82fd0863bc4d22 · report fixture: signature image_root:str/0/str, gt_root:str/0/str, batchsize:int/0/int, trainsize:int/0/int, shuffle:bool/0/bool, num_workers:int/0/int, pin_memory:bool/0/bool, augmentation:str/0/str · returned DataLoader · level recorded 2026-09-24
get_loader in 62 papers utils/dataloader_polyp.py ran licence not identified · pointer only · f9ba40e4610a2020 · report fixture: signature image_root:str/0/str, gt_root:str/0/str, batchsize:int/0/int, trainsize:int/0/int, shuffle:bool/0/bool, num_workers:int/0/int, pin_memory:bool/0/bool, augmentation:bool/0/bool, split:str/0/str, color_image:bool/0/bool · returned DataLoader · level recorded 2026-09-24
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
train_polyp.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 42eae5695451358c · report fixture: signature predicted:Tensor/2/float, labels:Tensor/2/float · returned Tensor · level recorded 2026-09-24
random_rot_flip in 12 papers utils/dataset_ACDC.py ran · violated contract fingerprinted no licence file found · pointer only · 960b785e65a00358 · report fixture: signature image:ndarray/2/float, label:ndarray/2/int · returned tuple · level recorded 2026-09-24
random_rotate in 18 papers utils/dataset_ACDC.py ran fingerprinted no licence file found · pointer only · 43fa66325ce3cafd · report fixture: signature image:ndarray/2/float, label:ndarray/2/int · returned tuple · level recorded 2026-09-24
resnet18 in 432 papers lib/resnet.py ran · our draft was wrong licence not identified · pointer only · a402cf18612ae9c6 · report fixture: signature pretrained:bool/0/bool, num_classes:int/0/int, deep_base:bool/0/bool, stem_width:int/0/int · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers lib/resnet.py ran · our draft was wrong licence not identified · pointer only · 14910065d80c5446 · report fixture: signature pretrained:bool/0/bool, num_classes:int/0/int, deep_base:bool/0/bool, stem_width:int/0/int · returned ResNet · level recorded 2026-09-24
structure_loss in 8 papers train_polyp.py ran licence not identified · pointer only · 13bf775ea00abd29 · report fixture: signature pred:Tensor/4/float, mask:Tensor/4/float, w:int/0/int · returned Tensor · level recorded 2026-09-24
EMCAD lib/decoders.py unverified licence not identified · pointer only · 2de61c75f45eb218 · report
MSCBLayer lib/decoders.py unverified licence not identified · pointer only · 0fb6e52cc17b4ebf · report
_init_weights in 9 papers lib/decoders.py unverified licence not identified · pointer only · 92c1ff2ae480fc0f · 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 EMCAD (graph method: EMCAD). 12 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. EMCAD entry · level 0 · unverified · 2de61c75f45eb218
  2. CAB model · level 1 · ran · 936d2bcb208f34c4
  3. EUCB model · level 1 · ran · 74c35cc1eda22a07
  4. LGAG model · level 1 · ran · c6413739abe9afc8
  5. MSCBLayer model · level 0 · unverified · 0fb6e52cc17b4ebf
  6. SAB model · level 1 · ran · 1afc66cfd19166c9
  7. _init_weights helper · level 0 · unverified · 92c1ff2ae480fc0f
  8. act_layer helper · level 1 · ran · our draft was wrong · bb51501828a7b35a
  9. channel_shuffle helper · level 1 · ran · our draft was wrong · b9da06d4f527dd6c
  10. MSCB helper · level 1 · ran · 9d62846b5a3faf10
  11. MSDC helper · level 1 · ran · 099a7b3762fb1d23
  12. gcd helper · level 1 · ran · honoured contract · a6fad4bca9a84fcf

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="2405.06880") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyDecoderImage SegmentationMedical Image AnalysisMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation 2018 Data Science Bowl EMCAD Dice 0.9274 #2 of 10 Archive leaderboard report
Medical Image Segmentation ACDC EMCAD Dice Score 0.9212 #4 of 6 Archive leaderboard report
Medical Image Segmentation Automatic Cardiac Diagnosis Challenge (ACDC) EMCAD Avg DSC 92.12 #8 of 20 Archive leaderboard report
Medical Image Segmentation BKAI-IGH NeoPolyp-Small EMCAD Average Dice 0.9296 #2 of 9 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB EMCAD mean Dice 0.9521 #3 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB EMCAD mean Dice 0.9231 #3 of 25 Archive leaderboard report
Medical Image Segmentation EM EMCAD DSC 95.53 #1 of 3 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB EMCAD mean Dice 0.9229 #4 of 25 Archive leaderboard report
Medical Image Segmentation ISIC 2018 EMCAD DSC 90.96 #1 of 2 Archive leaderboard report
Medical Image Segmentation ISIC 2018 EMCAD DSC 90.96 #3 of 5 Archive leaderboard report
Medical Image Segmentation ISIC2018 EMCAD mean Dice 0.9096 #3 of 3 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG EMCAD mean Dice 0.928 #16 of 58 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge EMCAD Avg DSC 83.63 #4 of 8 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge EMCAD Avg HD 15.68 #4 of 8 Archive leaderboard report
Medical Image Segmentation Synapse multi-organ CT EMCAD Avg DSC 83.63 #12 of 23 Archive leaderboard report
Medical Image Segmentation Synapse multi-organ CT EMCAD Avg HD 15.68 #12 of 23 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

Convolution

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