Papers › Semi-Supervised Semantic Segmentation with Cross-Consistency Training

Semi-Supervised Semantic Segmentation with Cross-Consistency Training

19 Mar 2020CVPR 2020 6arXiv:2003.09005archive 2025-07-28

Yassine Ouali, Céline Hudelot, Myriam Tami

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the cluster assumption, in which the decision boundary should lie in low-density regions. In this work, we first observe that for semantic segmentation, the low-density regions are more apparent within the hidden representations than within the inputs. We thus propose cross-consistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder. Concretely, a shared encoder and a main decoder are trained in a supervised manner using the available labeled examples. To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations. The proposed method is simple and can easily be extended to use additional training signal, such as image-level labels or pixel-level labels across different domains. We perform an ablation study to tease apart the effectiveness of each component, and conduct extensive experiments to demonstrate that our method achieves state-of-the-art results in several datasets.

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 20 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 19 samples from 2 repositories, 16 ran (8 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.

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. 1 of the 17 samples that ran has no recorded date.

yassouali/CCT officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
HiLab-git/DTC mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-supervised Medical Image Segmentation through Dual-task Consistency (arXiv:2009.04448; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Luoxd1996/DTC mentioned on GitHubpytorchMITSyntology: 18 samples, 15 ran (7 instrument-failed) · 3 unverified report
ZHKKKe/PixelSSL mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dbash/zerowaste mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bootstrapping Semantic Segmentation with Regional Contrast (arXiv:2104.04465; that paper's own run record: 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) · 3 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

20 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 9 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.

3ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
3ran; the contract check could not run
4ran
3unverified

Licence: 11 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 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 3 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.

yassouali/CCT official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
multi_scale_predict inference.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 60e3883cd6fa1a80 · report fixture: signature model:callable/0/?, image:Tensor/4/float, scales:list/1/float, num_classes:int/0/int, flip:bool/0/bool · returned ndarray · level recorded 2026-09-22
Luoxd1996/DTC community (archive-listed) 18 samples, 15 ran (7 instrument-failed) · 3 unverified
sigmoid_rampup in 22 papers code/utils/ramps.py ran · honoured contract fingerprinted MIT (permissive) · 3fb68ed6809a8085 · report fixture: signature current:int/0/int, rampup_length:int/0/int · returned float · level recorded, date not recorded
compute_dtm code/utils/losses_2.py ran MIT (permissive) · 133472fc12305a9c · report fixture: signature img_gt:ndarray/4/int, out_shape:tuple/1/int, normalize:bool/0/bool, fg:bool/0/bool · returned ndarray · level recorded 2026-09-25
compute_sdf in 5 papers code/utils/losses_2.py ran MIT (permissive) · 3b9f66ea3c6c5f9c · report fixture: signature img_gt:ndarray/4/float, out_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
cosine_rampdown in 15 papers code/utils/ramps.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 214e4ee9afcfa0e3 · report fixture: signature current:int/0/int, rampdown_length:int/0/int · returned float · level recorded 2026-09-22
decode_seg_map_sequence in 8 papers code/dataloaders/utils.py ran MIT (permissive) · 37fd4aff70632850 · report fixture: signature label_masks:list/1/ndarray, dataset:str/0/str · returned Tensor · level recorded 2026-09-25
dice in 32 papers code/utils/metrics.py ran fingerprinted MIT (permissive) · 271f6a7053a24e6c · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, ignore_index:NoneType/0/? · returned Tensor · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
code/utils/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9f3489c005e0165d · report fixture: signature score:Tensor/2/float, target:Tensor/2/int · returned Tensor · level recorded 2026-09-24
dice_loss1 in 8 papers code/utils/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 4953e4d45e6de492 · report fixture: signature score:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-24
encode_segmap in 9 papers code/dataloaders/utils.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 75e298e708abee58 · report fixture: signature mask:ndarray/3/int · returned ndarray · level recorded 2026-09-24
entropy_loss in 42 papers
census: 5 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
code/utils/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f8c429b95e4ae707 · report fixture: signature p:Tensor/2/float, C:int/0/int · returned Tensor · level recorded 2026-09-24
grouper in 19 papers code/dataloaders/la_heart.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c7ba8abbb7422762 · report fixture: signature iterable:list/1/int, n:int/0/int · returned zip · level recorded 2026-09-26
iterate_eternally in 11 papers code/dataloaders/la_heart.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 842cf7025c8045b6 · report fixture: signature indices:ndarray/1/int · returned chain · level recorded 2026-09-26
iterate_once in 12 papers code/dataloaders/la_heart.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 4232c309adddf9e4 · report fixture: signature iterable:list/1/int · returned ndarray · level recorded 2026-09-26
linear_rampup in 33 papers code/utils/ramps.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 069122bd5268cc56 · report fixture: signature current:int/0/int, rampup_length:int/0/int · returned float · level recorded 2026-09-25
recursive_glob in 12 papers code/dataloaders/utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f1e67bfcea91df50 · report fixture: signature rootdir:str/0/str, suffix:str/0/str · returned list · level recorded 2026-09-24
cal_dice in 5 papers code/utils/metrics.py unverified MIT (permissive) · ca40feece5ce04cb · report
hd_loss code/utils/losses_2.py unverified MIT (permissive) · 57c0f850206bf646 · report
load_model in 479 papers code/utils/util.py unverified MIT (permissive) here; the stored copy is pointer only · ad6309e2c80e2b00 · report
ZHKKKe/PixelSSL community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
pixelssl/ssl_algorithm/ssl_cct.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · dda77a33e14993ff · report fixture: returned Sequential · level recorded 2026-09-22

Tasks

DecoderSemantic SegmentationSemi-Supervised Semantic Segmentation

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