Papers › Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive...

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation

26 Jan 2021CVPR 2021 1arXiv:2101.10979archive 2025-07-28

Pan Zhang, Bo Zhang, Ting Zhang, Dong Chen, Yong Wang, Fang Wen

Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the discrepancy between source and target domains. In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation. In particular, we take one step further and exploit the feature distances from prototypes that provide richer information than mere prototypes. Specifically, we use it to estimate the likelihood of pseudo labels to facilitate online correction in the course of training. Meanwhile, we align the prototypical assignments based on relative feature distances for two different views of the same target, producing a more compact target feature space. Moreover, we find that distilling the already learned knowledge to a self-supervised pretrained model further boosts the performance. Our method shows tremendous performance advantage over state-of-the-art methods. We will make the code publicly available.

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 17 code samples harvested from 1 repository linked to this paper: 8 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

microsoft/ProDA officialmentioned on GitHubpytorchSyntology: 17 samples, 8 ran (2 instrument-failed) · 9 unverified report
E-DEEP/PapersReview mentioned on GitHubSyntology: not harvested 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

17 samples harvested: 8 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 9 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.

2ran · our draft was wrong
6ran
9unverified

Licence: 0 of the 17 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 microsoft/ProDA. “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 3 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.

microsoft/ProDA official repository 17 samples, 8 ran (2 instrument-failed) · 9 unverified
Bottleneck in 98 papers models/adaptation_modelv2.py ran · metamorphic tier: deterministic MIT (permissive) · 6020d23a07c55f29 · report fixture: returned Bottleneck · level recorded 2026-09-22
CallbackContext models/adaptation_modelv2.py ran MIT (permissive) · 0e7e99a49473a940 · report fixture: returned CallbackContext · level recorded 2026-09-22
Classifier_Module2 models/adaptation_modelv2.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7cfa9b72e3a4749d · report fixture: returned Classifier_Module2 · level recorded 2026-09-22
FCDiscriminator models/adaptation_modelv2.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 23029f57b971a963 · report fixture: returned FCDiscriminator · level recorded 2026-09-22
PolynomialLR models/adaptation_modelv2.py ran MIT (permissive) · 8a42c7371906d184 · report fixture: returned PolynomialLR · level recorded 2026-09-22
SEBlock in 14 papers models/adaptation_modelv2.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 332f8cc5d0d081e6 · report fixture: returned SEBlock · level recorded 2026-09-22
cross_entropy2d in 12 papers models/adaptation_modelv2.py ran · our draft was wrong MIT (permissive) · e48b895c94b5aa40 · report fixture: signature input:Tensor/4/float, target:Tensor/3/int, weight:Tensor/1/float, size_average:bool/0/bool, softmax_used:bool/0/bool, reduction:str/0/str, cls_num_list:NoneType/0/? · returned Tensor · level recorded 2026-09-22
get_scheduler in 122 papers models/adaptation_modelv2.py ran · our draft was wrong MIT (permissive) · 7101765897c8d17b · report fixture: signature optimizer:SGD/0/?, opt:OptConfig/0/? · returned PolynomialLR · level recorded 2026-09-22
CustomModel models/adaptation_modelv2.py unverified MIT (permissive) · 097fa03acb194ec7 · report
DataParallelWithCallback models/adaptation_modelv2.py unverified MIT (permissive) · 621eff113a744b84 · report
Deeplab in 7 papers models/adaptation_modelv2.py unverified MIT (permissive) · 5b7b14dc1a126e30 · report
ResNet101 in 11 papers models/adaptation_modelv2.py unverified MIT (permissive) · 724f27e7f6fe421c · report
affine_sample models/adaptation_modelv2.py unverified MIT (permissive) · 8abaace0beabbac9 · report
execute_replication_callbacks models/adaptation_modelv2.py unverified MIT (permissive) · 7308ae70af0cb672 · report
feat_prototype_distance_module models/adaptation_modelv2.py unverified MIT (permissive) · c0389bd83130fd48 · report
freeze_bn models/adaptation_modelv2.py unverified MIT (permissive) · fa564b743e0f7020 · report
freeze_bn_func models/adaptation_modelv2.py unverified MIT (permissive) · 692f2a64673cce1b · 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 Prototypical Pseudo Label Denoising and Target Structure Learning (graph method: Prototypical Pseudo Label Denoising and Target Structure Learning). 24 bricks; individually on a fixture: 15 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. CustomModel entry · level 0 · unverified · 097fa03acb194ec7
  2. DataParallelWithCallback helper · level 0 · unverified · 621eff113a744b84
  3. Deeplab helper · level 0 · unverified · 5b7b14dc1a126e30
  4. FCDiscriminator helper · level 1 · ran · 23029f57b971a963
  5. SynchronizedBatchNorm2d helper · level 1 · ran · e6f91e80712a76dd
  6. affine_sample helper · level 0 · unverified · 8abaace0beabbac9
  7. cross_entropy2d helper · level 1 · ran · our draft was wrong · e48b895c94b5aa40
  8. feat_prototype_distance_module model · level 0 · unverified · c0389bd83130fd48
  9. freeze_bn helper · level 0 · unverified · fa564b743e0f7020
  10. get_scheduler helper · level 1 · ran · our draft was wrong · 7101765897c8d17b
  11. execute_replication_callbacks helper · level 0 · unverified · 7308ae70af0cb672
  12. Bottleneck helper · level 1 · ran · 6020d23a07c55f29
  13. ResNet101 helper · level 0 · unverified · 724f27e7f6fe421c
  14. freeze_bn_func helper · level 0 · unverified · 692f2a64673cce1b
  15. _SynchronizedBatchNorm helper · level 1 · ran · 9f557ce8389a603f
  16. PolynomialLR helper · level 1 · ran · 8a42c7371906d184
  17. CallbackContext helper · level 1 · ran · 0e7e99a49473a940
  18. Classifier_Module2 helper · level 1 · ran · 7cfa9b72e3a4749d
  19. SyncMaster helper · level 1 · ran · 93f1be24e0653bc8
  20. _sum_ft helper · level 1 · ran · violated contract · 3151cee68a1020dc
  21. _unsqueeze_ft helper · level 1 · ran · honoured contract · 1efd43bcf31727c0
  22. SEBlock helper · level 1 · ran · 332f8cc5d0d081e6
  23. FutureResult helper · level 1 · ran · 9e8c636cac1d847f
  24. SlavePipe helper · level 1 · ran · e75aa93b78286d50

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="2101.10979") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain AdaptationImage-to-Image TranslationPseudo LabelSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation GTA5 to Cityscapes ProDA mIoU 57.5 #21 of 28 Archive leaderboard report
Image-to-Image Translation GTAV-to-Cityscapes Labels ProDA mIoU 57.5 #15 of 22 Archive leaderboard report
Image-to-Image Translation SYNTHIA-to-Cityscapes ProDA mIoU (13 classes) 62.0 #11 of 28 Archive leaderboard report
Semantic Segmentation GTAV-to-Cityscapes Labels ProDA mIoU 57.5 #10 of 12 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels ProDA(with knowledge distillation) mIoU 57.5 #24 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes ProDA(ResNet-101) MIoU (13 classes) 62.0 #16 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes ProDA(ResNet-101) MIoU (16 classes) 55.5 #16 of 38 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

1x1 ConvolutionASPPBatch NormalizationDeepLabv3Dilated ConvolutionSpatial Pyramid Pooling

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