Papers › Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
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.
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):
get_harvested_code_for_paper(arxiv_id="2106.01226")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2106.01226", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2106.01226")
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.
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.
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.
3bcf2f021ec54810 · report
fixture: signature input:Tensor/4/float, target:Tensor/4/float · returned Tensor · level recorded 2026-09-25 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 c48d876b9a3ae27a · report
fixture: signature matrix:Tensor/4/float · returned Tensor · level recorded 2026-09-26 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 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 636b23389eba27a1 · report
835ca2564a9653a6 · report
43976b9c757e2931 · report
fixture: returned BaseLR · level recorded 2026-09-22 7376c94156eef50e · report
fixture: returned DepthTrainPre · level recorded 2026-09-22 0525b2902320166f · report
fixture: returned DepthValPre · level recorded 2026-09-22 ee5ad1935ccce67d · report
fixture: returned RGBDTrainPre · level recorded 2026-09-22 fa35dd778049b33e · report
fixture: returned RGBDValPre · level recorded 2026-09-22 aec285de0ab732b7 · report
fixture: returned RGBTrainPre · level recorded 2026-09-22 8db3a8167f167a90 · report
fixture: returned RGBValPre · level recorded 2026-09-22 f1fa2c7b643051a4 · report
fixture: returned WarmUpPolyLR · level recorded 2026-09-22 de4ac68ef98bebc8 · report
fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-22 e74fcb04fd589c71 · report
fixture: signature results:list/1/dict, num_classes:int/0/int · returned tuple · level recorded 2026-09-22 203e73feddb57884 · report
fixture: signature hist:ndarray/2/float, correct:float/0/float, labeled:float/0/float · returned tuple · level recorded 2026-09-22 9e85fa995eda358a · report
fixture: signature n_cl:int/0/int, pred:ndarray/1/int, gt:ndarray/1/int · returned tuple · level recorded 2026-09-22 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 815e160273134736 · report
fixture: signature img:ndarray/2/int · returned ndarray · level recorded 2026-09-22 356686ea476b6ce4 · report
fixture: signature imgs:dict/0/? · returned dict · level recorded 2026-09-22 ee31a169e3121523 · report
fixture: signature imgs:dict/0/?, scale_array:list/1/float, orig_size:tuple/1/int · returned tuple · level recorded 2026-09-22 cdc6961513bc7352 · report
fixture: signature depth:ndarray/2/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22 f385fb867a898c19 · report
fixture: signature gt:ndarray/3/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22 b7dfd9cbf7eedacb · report
fixture: signature rgb:ndarray/3/int, expectedshape:tuple/1/int · returned ndarray · level recorded 2026-09-22 7c76a16e37d76d1d · report
fbf76f33c68cc257 · report
4f9f5a818fe83273 · report
fabc41fbf8341410 · report
891adce76c9b1ef4 · report
74ffeedbf2acc130 · report
7dbd86b9ed974d1c · report
17881896b84793bf · report
35bbfab3ce7415bc · report
c6cd5ad91c3a2851 · report
fixture: signature loaded_png:ndarray/3/int · returned ndarray · level recorded 2026-09-24 74dcea3d4dcc90a5 · report
fixture: signature loaded_png:ndarray/2/int · returned ndarray · level recorded 2026-09-24 a2c8b38ba9393780 · report
fixture: signature seg:ndarray/3/int · returned ndarray · level recorded 2026-09-25 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.
- CPSFramework entry · level 0 · unverified ·
fbf76f33c68cc257 - AbstractFramework helper · level 0 · unverified ·
7c76a16e37d76d1d - WarmUpPolyLR helper · level 1 · ran ·
f1fa2c7b643051a4 - compute_metrics helper · level 1 · ran · honoured contract ·
e74fcb04fd589c71 - get_train_loader helper · level 0 · unverified ·
74ffeedbf2acc130 - get_val_loader helper · level 0 · unverified ·
7dbd86b9ed974d1c - hist_info helper · level 1 · ran; the contract check could not run (RAISES) ·
9e85fa995eda358a - BaseLR helper · level 1 · ran ·
43976b9c757e2931 - compute_score helper · level 1 · ran · our draft was wrong ·
203e73feddb57884 - get_preprocessors helper · level 0 · unverified ·
891adce76c9b1ef4 - _sliding_collate_fn helper · level 1 · ran · our draft was wrong ·
de4ac68ef98bebc8 - DepthTrainPre helper · level 1 · ran ·
7376c94156eef50e - DepthValPre helper · level 1 · ran ·
0525b2902320166f - RGBDTrainPre helper · level 1 · ran ·
ee5ad1935ccce67d - RGBDValPre helper · level 1 · ran ·
fa35dd778049b33e - RGBTrainPre helper · level 1 · ran ·
aec285de0ab732b7 - RGBValPre helper · level 1 · ran ·
8db3a8167f167a90 - normalizedepth helper · level 1 · ran · violated contract ·
815e160273134736 - random_crop_pad_to_shape helper · level 0 · unverified ·
35bbfab3ce7415bc - random_mirror helper · level 1 · ran · our draft was wrong ·
356686ea476b6ce4 - random_scale helper · level 1 · ran · our draft was wrong ·
ee31a169e3121523 - resizedepth helper · level 1 · ran; the contract check could not run (RAISES) ·
cdc6961513bc7352 - normalize helper · level 1 · ran · violated contract ·
17cb5b0dfa01b491 - resizergb helper · level 1 · ran; the contract check could not run (RAISES) ·
b7dfd9cbf7eedacb - generate_random_crop_pos helper · level 0 · unverified ·
4f9f5a818fe83273 - get_2dshape helper · level 0 · unverified ·
fabc41fbf8341410 - pad_image_to_shape helper · level 0 · unverified ·
17881896b84793bf - 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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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