Papers › Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

2 Jun 2021CVPR 2021 1arXiv:2106.01226archive 2025-07-28

Xiaokang Chen, Yuhui Yuan, Gang Zeng, Jingdong Wang

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.

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 39 code samples harvested from 3 repositories linked to this paper: 27 ran (of which 8 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 4 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 5 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: official repository: 7 samples from 1 repository, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 32 samples from 2 repositories, 22 ran (14 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 27 samples that ran has no recorded date.

charlesCXK/TorchSemiSeg officialmentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (1 instrument-failed) · 2 unverified report
harshm121/m3l mentioned on GitHubpytorchSyntology: 28 samples, 19 ran (8 instrument-failed) · 9 unverified report
yhuang1997/3D-CPS mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 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

39 samples harvested: 27 ran (of which 8 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 4 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 12 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.

2ran · honoured contract
4ran · violated contract
5ran · our draft was wrong
4ran; the contract check could not run
12ran
12unverified

Licence: 34 of the 39 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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”. For 1 sample 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.

charlesCXK/TorchSemiSeg official repository 7 samples, 5 ran (1 instrument-failed) · 2 unverified
bce2d furnace/seg_opr/loss_opr.py ran fingerprinted MIT (permissive) · 3bcf2f021ec54810 · report fixture: signature input:Tensor/4/float, target:Tensor/4/float · returned Tensor · level recorded 2026-09-25
conv3x3 in 1,376 papers furnace/base_model/hrnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is 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
log_det_by_cholesky furnace/seg_opr/rmi_loss.py ran MIT (permissive) · c48d876b9a3ae27a · report fixture: signature matrix:Tensor/4/float · returned Tensor · level recorded 2026-09-26
map_get_pairs furnace/seg_opr/rmi_loss.py ran MIT (permissive) · 97f5e3b69f2c69ea · report fixture: signature labels_4D:Tensor/4/int, probs_4D:Tensor/4/float, radius:int/0/int, is_combine:bool/0/bool · returned Tensor · level recorded 2026-09-25
map_get_pairs_region furnace/seg_opr/rmi_loss.py ran MIT (permissive) · 99b42d109e83351a · report fixture: signature labels_4D:Tensor/4/float, probs_4D:Tensor/4/float, radius:int/0/int, is_combine:int/0/int, num_classeses:int/0/int · returned tuple · level recorded 2026-09-26
get_seg_hrnet_w18s furnace/base_model/hrnet.py unverified MIT (permissive) here; the stored copy is pointer only · 636b23389eba27a1 · report
get_seg_hrnet_w48 furnace/base_model/hrnet.py unverified MIT (permissive) here; the stored copy is pointer only · 835ca2564a9653a6 · report
harshm121/m3l community (archive-listed) 28 samples, 19 ran (8 instrument-failed) · 9 unverified
BaseLR src/semi_supervised/cps.py ran no licence file found · pointer only · 43976b9c757e2931 · report fixture: returned BaseLR · level recorded 2026-09-22
DepthTrainPre src/semi_supervised/cps.py ran no licence file found · pointer only · 7376c94156eef50e · report fixture: returned DepthTrainPre · level recorded 2026-09-22
DepthValPre src/semi_supervised/cps.py ran fingerprinted no licence file found · pointer only · 0525b2902320166f · report fixture: returned DepthValPre · level recorded 2026-09-22
RGBDTrainPre src/semi_supervised/cps.py ran no licence file found · pointer only · ee5ad1935ccce67d · report fixture: returned RGBDTrainPre · level recorded 2026-09-22
RGBDValPre src/semi_supervised/cps.py ran no licence file found · pointer only · fa35dd778049b33e · report fixture: returned RGBDValPre · level recorded 2026-09-22
RGBTrainPre src/semi_supervised/cps.py ran no licence file found · pointer only · aec285de0ab732b7 · report fixture: returned RGBTrainPre · level recorded 2026-09-22
RGBValPre src/semi_supervised/cps.py ran no licence file found · pointer only · 8db3a8167f167a90 · report fixture: returned RGBValPre · level recorded 2026-09-22
WarmUpPolyLR src/semi_supervised/cps.py ran no licence file found · pointer only · f1fa2c7b643051a4 · report fixture: returned WarmUpPolyLR · level recorded 2026-09-22
_sliding_collate_fn src/semi_supervised/cps.py ran · our draft was wrong no licence file found · pointer only · de4ac68ef98bebc8 · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-22
compute_metrics in 208 papers src/semi_supervised/cps.py ran · honoured contract no licence file found · pointer only · e74fcb04fd589c71 · report fixture: signature results:list/1/dict, num_classes:int/0/int · returned tuple · level recorded 2026-09-22
compute_score in 49 papers src/semi_supervised/cps.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 203e73feddb57884 · report fixture: signature hist:ndarray/2/float, correct:float/0/float, labeled:float/0/float · returned tuple · level recorded 2026-09-22
hist_info src/semi_supervised/cps.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9e85fa995eda358a · report fixture: signature n_cl:int/0/int, pred:ndarray/1/int, gt:ndarray/1/int · returned tuple · 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
src/semi_supervised/cps.py ran · violated contract fingerprinted no licence file found · pointer only · 17cb5b0dfa01b491 · report fixture: signature img:ndarray/4/int, mean:ndarray/1/float, std:ndarray/1/float · returned ndarray · level recorded 2026-09-22
normalizedepth src/semi_supervised/cps.py ran · violated contract fingerprinted no licence file found · pointer only · 815e160273134736 · report fixture: signature img:ndarray/2/int · returned ndarray · level recorded 2026-09-22
random_mirror in 7 papers src/semi_supervised/cps.py ran · our draft was wrong no licence file found · pointer only · 356686ea476b6ce4 · report fixture: signature imgs:dict/0/? · returned dict · level recorded 2026-09-22
random_scale in 9 papers src/semi_supervised/cps.py ran · our draft was wrong no licence file found · pointer only · ee31a169e3121523 · report fixture: signature imgs:dict/0/?, scale_array:list/1/float, orig_size:tuple/1/int · returned tuple · level recorded 2026-09-22
resizedepth src/semi_supervised/cps.py ran; the contract check could not run (RAISES) no licence file found · pointer only · cdc6961513bc7352 · report fixture: signature depth:ndarray/2/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22
resizegt src/semi_supervised/cps.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f385fb867a898c19 · report fixture: signature gt:ndarray/3/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22
resizergb src/semi_supervised/cps.py ran; the contract check could not run (RAISES) no licence file found · pointer only · b7dfd9cbf7eedacb · report fixture: signature rgb:ndarray/3/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22
AbstractFramework src/semi_supervised/cps.py unverified no licence file found · pointer only · 7c76a16e37d76d1d · report
CPSFramework src/semi_supervised/cps.py unverified no licence file found · pointer only · fbf76f33c68cc257 · report
generate_random_crop_pos src/semi_supervised/cps.py unverified no licence file found · pointer only · 4f9f5a818fe83273 · report
get_2dshape src/semi_supervised/cps.py unverified no licence file found · pointer only · fabc41fbf8341410 · report
get_preprocessors src/semi_supervised/cps.py unverified no licence file found · pointer only · 891adce76c9b1ef4 · report
get_train_loader in 12 papers src/semi_supervised/cps.py unverified no licence file found · pointer only · 74ffeedbf2acc130 · report
get_val_loader src/semi_supervised/cps.py unverified no licence file found · pointer only · 7dbd86b9ed974d1c · report
pad_image_to_shape src/semi_supervised/cps.py unverified no licence file found · pointer only · 17881896b84793bf · report
random_crop_pad_to_shape src/semi_supervised/cps.py unverified no licence file found · pointer only · 35bbfab3ce7415bc · report
yhuang1997/3D-CPS community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
convert_CT_seg nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py ran · violated contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · c6cd5ad91c3a2851 · report fixture: signature loaded_png:ndarray/3/int · returned ndarray · level recorded 2026-09-24
convert_MR_seg nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 74dcea3d4dcc90a5 · report fixture: signature loaded_png:ndarray/2/int · returned ndarray · level recorded 2026-09-24
convert_labels_back_to_BraTS in 11 papers nnunet/dataset_conversion/Task032_BraTS_2018.py ran · violated contract fingerprinted Apache-2.0 (permissive) · a2c8b38ba9393780 · report fixture: signature seg:ndarray/3/int · returned ndarray · level recorded 2026-09-25
load_png_stack nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 29176ca87f23c2d7 · 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 Cross Pseudo Supervision (graph method: Cross Pseudo Supervision). 28 bricks; individually on a fixture: 19 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. CPSFramework entry · level 0 · unverified · fbf76f33c68cc257
  2. AbstractFramework helper · level 0 · unverified · 7c76a16e37d76d1d
  3. WarmUpPolyLR helper · level 1 · ran · f1fa2c7b643051a4
  4. compute_metrics helper · level 1 · ran · honoured contract · e74fcb04fd589c71
  5. get_train_loader helper · level 0 · unverified · 74ffeedbf2acc130
  6. get_val_loader helper · level 0 · unverified · 7dbd86b9ed974d1c
  7. hist_info helper · level 1 · ran; the contract check could not run (RAISES) · 9e85fa995eda358a
  8. BaseLR helper · level 1 · ran · 43976b9c757e2931
  9. compute_score helper · level 1 · ran · our draft was wrong · 203e73feddb57884
  10. get_preprocessors helper · level 0 · unverified · 891adce76c9b1ef4
  11. _sliding_collate_fn helper · level 1 · ran · our draft was wrong · de4ac68ef98bebc8
  12. DepthTrainPre helper · level 1 · ran · 7376c94156eef50e
  13. DepthValPre helper · level 1 · ran · 0525b2902320166f
  14. RGBDTrainPre helper · level 1 · ran · ee5ad1935ccce67d
  15. RGBDValPre helper · level 1 · ran · fa35dd778049b33e
  16. RGBTrainPre helper · level 1 · ran · aec285de0ab732b7
  17. RGBValPre helper · level 1 · ran · 8db3a8167f167a90
  18. normalizedepth helper · level 1 · ran · violated contract · 815e160273134736
  19. random_crop_pad_to_shape helper · level 0 · unverified · 35bbfab3ce7415bc
  20. random_mirror helper · level 1 · ran · our draft was wrong · 356686ea476b6ce4
  21. random_scale helper · level 1 · ran · our draft was wrong · ee31a169e3121523
  22. resizedepth helper · level 1 · ran; the contract check could not run (RAISES) · cdc6961513bc7352
  23. normalize helper · level 1 · ran · violated contract · 17cb5b0dfa01b491
  24. resizergb helper · level 1 · ran; the contract check could not run (RAISES) · b7dfd9cbf7eedacb
  25. generate_random_crop_pos helper · level 0 · unverified · 4f9f5a818fe83273
  26. get_2dshape helper · level 0 · unverified · fabc41fbf8341410
  27. pad_image_to_shape helper · level 0 · unverified · 17881896b84793bf
  28. resizegt helper · level 1 · ran; the contract check could not run (RAISES) · f385fb867a898c19

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="2106.01226") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) Validation mIoU 77.62% #11 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) Validation mIoU 79.21% #9 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) Validation mIoU 80.21% #7 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled CPS (DeepLab v3+ with ResNet-101) Validation mIoU 69.8 #18 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 183 labeled CPS (DeepLab v3+ with ResNet-101) Validation mIoU 67.4 #15 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) Validation mIoU 77.68% #16 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 366 labeled CPS (DeepLab v3+ with ResNet-101) Validation mIoU 71.7 #15 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 732 labeled CPS (DeepLab v3+ with ResNet-101) Validation mIoU 75.9 #15 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 92 labeled CPS (DeepLab v3+ with ResNet-101) Validation mIoU 64.1 #16 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled CPS Validation mIoU 76.44% #15 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI CPS (Range View) mIoU (1% Labels) 33.7 #8 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI CPS (Range View) mIoU (10% Labels) 50.0 #8 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI CPS (Range View) mIoU (20% Labels) 52.8 #8 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI CPS (Range View) mIoU (50% Labels) 54.6 #8 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI CPS (Range View) mIoU (1% Labels) 36.5 #12 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI CPS (Range View) mIoU (10% Labels) 52.3 #12 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI CPS (Range View) mIoU (20% Labels) 56.3 #12 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI CPS (Range View) mIoU (50% Labels) 57.4 #12 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation WoodScape CPS Mean IoU 62.87 #2 of 2 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes CPS (Range View) mIoU (1% Labels) 40.7 #10 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes CPS (Range View) mIoU (10% Labels) 60.8 #10 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes CPS (Range View) mIoU (20% Labels) 64.9 #10 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes CPS (Range View) mIoU (50% Labels) 68.0 #10 of 11 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.

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