Papers › Domain-Adversarial Training of Neural Networks

Domain-Adversarial Training of Neural Networks

28 May 2015arXiv:1505.07818archive 2025-07-28

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.

PaperPDFCodeCode 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 52 code samples: 50 from 17 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 52: 35 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 17 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 16 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: community (archive-listed): 50 samples from 17 repositories, 34 ran (18 with no instrument failure; 16 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 12 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.

37 repositories listed; official and paper-mentioned ones first.

AKASH2907/Forgery-Classification-via-Domain-Adaptation mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (4 instrument-failed) · 2 unverified report
Darth-Kronos/Unsupervised-Domain-Adaptation mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
JorisRoels/domain-adaptive-segmentation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep CORAL: Correlation Alignment for Deep Domain Adaptation (arXiv:1607.01719; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
MarvinMartin24/MADA-PL mentioned on GitHubpytorchSyntology: 8 samples, 7 ran (6 instrument-failed) · 1 unverified report
Nadavc220/DomainAdversarialTrainingOfNeuralNetworks mentioned on GitHubpytorchSyntology: not harvested report
ShichengChen/Domain-Adversarial-Training-of-Neural-Networks mentioned on GitHubpytorchMITSyntology: not harvested report
ShichengChen/WaveNetSeparateAudio mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to WaveNet: A Generative Model for Raw Audio (arXiv:1609.03499; that paper's own run record: 65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified); nothing checks that they implement this paper's method. report
antoinedemathelin/wann mentioned on GitHubtfSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
anuraggoel70/Domain-Adversarial-Training-of-Neural-Networks mentioned on GitHubSyntology: not harvested report
asahi417/DeepDomainAdaptation mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation (arXiv:1803.10081; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
calico/scnym mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
criteo-research/pytorch-ada mentioned on GitHubpytorchSyntology: 9 samples, 6 ran (4 instrument-failed) · 3 unverified report
dv-fenix/Domain-Adaptation mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
erlendd/ddan mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Batch Normalization For Practical Domain Adaptation (arXiv:1603.04779; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/DomainBed mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
gabrieletiboni/Domain-adaptation-on-PACS-dataset mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
gentlezhu/shift-robust-gnns mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data (arXiv:2108.01099; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
lywang12/cupi-domain mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lywang12/cuti-domain mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lzx6/pytorch_DA mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mashaan14/DANN-toy mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Domain Adaptation by Backpropagation (arXiv:1409.7495; that paper's own run record: 34 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 12 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
monkey0head/Domain_Adaptation_thesis mentioned on GitHubpytorchSyntology: not harvested report
rpryzant/proxy-a-distance mentioned on GitHubMITSyntology: not harvested report
sangdon/pac-ps-w mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
scpark20/universal-music-translation mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
tachitachi/GradientReversal mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Domain Adaptation by Backpropagation (arXiv:1409.7495; that paper's own run record: 34 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 12 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
thuml/Transfer-Learning-Library mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Domain Adaptation by Backpropagation (arXiv:1409.7495; that paper's own run record: 34 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 12 where Syntology's instrument failed) · 7 unverified), Learning Transferable Features with Deep Adaptation Networks (arXiv:1502.02791; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), Deep CORAL: Correlation Alignment for Deep Domain Adaptation (arXiv:1607.01719; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
timgaripov/asa mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
vcoyette/DANN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
vict0rsch/ArxivTools mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
vict0rsch/PaperMemory mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World (arXiv:1703.06907; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
vict0rsch/arxiv-pdf-abs mentioned on GitHubpytorchMITSyntology: not harvested report
vihari/crossgrad mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generalizing Across Domains via Cross-Gradient Training (arXiv:1804.10745; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
domainadaptation/salad pytorchMPL-2.0Syntology: not harvested report
kevinmusgrave/pytorch-adapt pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep CORAL: Correlation Alignment for Deep Domain Adaptation (arXiv:1607.01719; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified), Adversarial Discriminative Domain Adaptation (arXiv:1702.05464; that paper's own run record: 14 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; 7 where Syntology's instrument failed) · 34 unverified), Conditional Adversarial Domain Adaptation (arXiv:1705.10667; that paper's own run record: 0 ran · 3 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
michiel-j/DANN-two-moons-PyTorch pytorchSyntology: 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.

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

52 samples harvested: 35 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 17 where Syntology's instrument failed) · 17 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.

1ran · honoured contract
16ran · our draft was wrong
1ran; the contract check could not run
17ran
17unverified

Licence: 22 of the 52 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 17 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. 2 samples are listed last, in a group without a repository. “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 2 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.

AKASH2907/Forgery-Classification-via-Domain-Adaptation community (archive-listed) 6 samples, 4 ran (4 instrument-failed) · 2 unverified
alexnet in 42 papers DANN/dann_keras.py ran · our draft was wrong no licence file found · pointer only · d86e29f3ca97a8c2 · report fixture: signature inputs:KerasTensor/0/float · returned KerasTensor · level recorded 2026-09-22
batch_generator in 8 papers DANN/dann_keras.py ran · our draft was wrong no licence file found · pointer only · 4a9bc68de4ae0c55 · report fixture: signature data:list/1/ndarray, batch_size:int/0/int · returned generator · level recorded 2026-09-22
build_models in 10 papers DANN/dann_keras.py ran · our draft was wrong no licence file found · pointer only · f9776e8c18b947b6 · report fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22
vgg_16 DANN/dann_keras.py ran · our draft was wrong no licence file found · pointer only · 851159feffea3b04 · report fixture: signature inputs:KerasTensor/0/float · returned KerasTensor · level recorded 2026-09-22
train in 522 papers DANN/dann_keras.py unverified no licence file found · pointer only · 1e5fb974a2b9088c · report
write_log in 6 papers DANN/dann_keras.py unverified no licence file found · pointer only · 882f695d04b3d5b7 · report
Darth-Kronos/Unsupervised-Domain-Adaptation community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ReverseLayerF DANN/model.py ran MIT (permissive) · 917fb058e1f4bb05 · report fixture: returned ReverseLayerF · level recorded 2026-09-22
DANNModel DANN/model.py unverified MIT (permissive) · 9e554f3838a1af56 · report
MarvinMartin24/MADA-PL community (archive-listed) 8 samples, 7 ran (6 instrument-failed) · 1 unverified
GRL Models/nets/MADA.py ran MIT (permissive) · 3ce4eba45b4ca3fc · report fixture: returned GRL · level recorded 2026-09-22
linear2_bn Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · cd9167b485a751fd · report fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22
linear2_dr2_bn Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · 3e123903386d5131 · report fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22
linear3_bn2_v1 Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · cec816fd8905007d · report fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22
linear3_bn2_v2 Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · 946555f6a21e149f · report fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22
load_backbone in 6 papers Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · f64f43c34c4542e9 · report fixture: signature name:str/0/str, pretrained:bool/0/bool · returned tuple · level recorded 2026-09-22
load_classifier in 7 papers Models/nets/MADA.py ran · our draft was wrong MIT (permissive) · 8d9374ad6935ac3d · report fixture: signature name:str/0/str, input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22
MADA Models/nets/MADA.py unverified MIT (permissive) · e61d73732bf10468 · report
antoinedemathelin/wann community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
_GradReverse wann/methods/WANN.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4c1fc418e3779b2d · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
_get_default_model wann/methods/WANN.py ran · our draft was wrong no licence file found · pointer only · ff4ee6a4efd6ea00 · report fixture: signature shape:int/0/int, activation:str/0/str, C:int/0/int, name:str/0/str · returned Functional · level recorded 2026-09-22
_grad_reverse wann/methods/WANN.py ran · honoured contract fingerprinted no licence file found · pointer only · 138b0d8c38a323bc · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
WANN wann/methods/WANN.py unverified no licence file found · pointer only · 95838026a4f67e63 · report
calico/scnym community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
CellTypeCLF scnym/model.py ran fingerprinted Apache-2.0 (permissive) · e2db8a3a21c6bf4c · report fixture: returned CellTypeCLF · level recorded 2026-09-22
GradReverse in 12 papers scnym/model.py ran Apache-2.0 (permissive) · 1a6a7062274a346d · report fixture: returned GradReverse · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
scnym/model.py ran Apache-2.0 (permissive) · 1a8c0c365eb16cdc · report fixture: returned ResBlock · level recorded 2026-09-22
DANN in 5 papers scnym/model.py unverified Apache-2.0 (permissive) · cd0abd234c0eba6b · report
criteo-research/pytorch-ada community (archive-listed) 9 samples, 6 ran (4 instrument-failed) · 3 unverified
BaseAdaptTrainer adalib/ada/models/architectures.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0e5b0fea39063b16 · report fixture: returned BaseAdaptTrainer · level recorded 2026-09-22
ReverseLayerF adalib/ada/models/architectures.py ran Apache-2.0 (permissive) · a9713d2fe23f5ada · report fixture: returned ReverseLayerF · level recorded 2026-09-22
cross_entropy_logits adalib/ada/models/architectures.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 310d54a1dd86ec79 · report fixture: signature linear_output:Tensor/2/float, label:Tensor/1/int, weights:Tensor/1/float · returned tuple · level recorded 2026-09-22
get_aggregated_metrics adalib/ada/models/architectures.py ran · our draft was wrong Apache-2.0 (permissive) · 4113c2e807d432ee · report fixture: signature metric_name_list:list/1/str, metric_outputs:list/1/dict · returned dict · level recorded 2026-09-22
get_aggregated_metrics_from_dict adalib/ada/models/architectures.py ran · our draft was wrong Apache-2.0 (permissive) · 61fd42a2e2a7cfcc · report fixture: signature input_metric_dict:dict/0/? · returned dict · level recorded 2026-09-22
get_metrics_from_parameter_dict adalib/ada/models/architectures.py ran · our draft was wrong Apache-2.0 (permissive) · 704df3b8019c2aa5 · report fixture: signature parameter_dict:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-22
BaseDANNLike adalib/ada/models/architectures.py unverified Apache-2.0 (permissive) · 6ca780e6cedb8469 · report
DANNtrainer adalib/ada/models/architectures.py unverified Apache-2.0 (permissive) · b69e7e3bd38b5a79 · report
Method in 5 papers adalib/ada/models/architectures.py unverified Apache-2.0 (permissive) · c0ae116e1108bfcf · report
dv-fenix/Domain-Adaptation community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
DANN in 5 papers Domain-Adversarial Training of Neural Networks/model.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 59f8b8a3c0a6bdfe · report fixture: signature inputs:Tensor/4/float, completion_lambda:float/0/float · returned tuple · level recorded 2026-09-22
GradientReversalLayer in 6 papers Domain-Adversarial Training of Neural Networks/model.py unverified GPL-3.0 (copyleft) · pointer only · a5f777ab36b3f81e · report
facebookresearch/DomainBed community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AbstractDANN domainbed/algorithms.py ran MIT (permissive) · 8a387c444dc4c6a4 · report fixture: returned AbstractDANN · level recorded 2026-09-22
gabrieletiboni/Domain-adaptation-on-PACS-dataset community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AlexNetDANN CODE/models/AlexNetDANN.py ran · metamorphic tier: invariant no licence file found · pointer only · c601b6f644d029af · report fixture: signature x:Tensor/4/float, alpha:float/0/float, dest:str/0/str · returned Tensor · level recorded 2026-09-22
lywang12/cupi-domain community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ClassifierBase utils/network.py ran fingerprinted no licence file found · pointer only · f70dbf08bbfa9c34 · report fixture: signature x:Tensor/4/float, y:Tensor/4/float, z:Tensor/4/float, action:str/0/str · returned tuple · level recorded 2026-09-24
lywang12/cuti-domain community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AdversarialNetwork utils/network.py ran · metamorphic tier: deterministic no licence file found · pointer only · f1707c22da402ad3 · report fixture: returned AdversarialNetwork · level recorded 2026-09-22
lzx6/pytorch_DA community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Discriminator in 42 papers models/model.py ran no licence file found · pointer only · 87db2131110dfd0a · report fixture: returned Discriminator · level recorded 2026-09-22
GradReverse in 12 papers models/model.py ran no licence file found · pointer only · 22d411c2795ced15 · report fixture: returned GradReverse · level recorded 2026-09-22
sangdon/pac-ps-w community (archive-listed) 1 sample, 0 ran · 1 unverified
DANN in 5 papers model/da.py unverified no licence file found · pointer only · fcde4e5aa7af7696 · report
scpark20/universal-music-translation community (archive-listed) 1 sample, 0 ran · 1 unverified
domain_confusion music_trans.py unverified GPL-3.0 (copyleft) · pointer only · 48ebff402229f303 · report
timgaripov/asa community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
entropy in 112 papers
census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32
support_alignment/core/algorithms.py ran · our draft was wrong fingerprinted MIT (permissive) · 5b9be386bbb3d10e · report fixture: signature logits:Tensor/2/float · returned Tensor · level recorded 2026-09-22
AbstrtactDiscriminatorAlignment support_alignment/core/algorithms.py unverified MIT (permissive) · aa6ec272928f9093 · report
DANN in 5 papers support_alignment/core/algorithms.py unverified MIT (permissive) · b140a1b50f334aa6 · report
vcoyette/DANN community (archive-listed) 1 sample, 0 ran · 1 unverified
FeatureExtractor in 24 papers models/mnist.py unverified no licence file found · pointer only · 3d0632c955417561 · report
vict0rsch/ArxivTools community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
common_shape extra/imgs/concat.py ran MIT (permissive) · 2fb3457e6f433bd8 · report fixture: signature imgs:list/1/ndarray, axis:int/0/int · returned tuple · level recorded 2026-09-26
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
extra/imgs/concat.py ran MIT (permissive) · 2e5319a051a23ef3 · report fixture: signature img:ndarray/3/int, min_h:int/0/int, min_w:NoneType/0/? · returned ndarray · level recorded 2026-09-26
to_rgba extra/imgs/concat.py unverified MIT (permissive) · 5773872947986444 · report
Repository not located 2 samples, 1 ran (1 instrument-failed) · 1 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
grl_hook in 11 papers repository not located ran · our draft was wrong licence of this copy not recorded · 9768efb52f591b55 · report fixture: signature coeff:float/0/float · returned function · level recorded 2026-09-22
calc_coeff in 14 papers repository not located unverified licence of this copy not recorded · e352afa5762c5a6b · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

17 assemblies on this paper: 17 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

17 sibling assemblies for Domain-Adversarial Training of Neural Networks (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 17 sibling assemblies; the other 5 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 4 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. AdversarialNetwork entry · level 1 · ran · f1707c22da402ad3
  2. calc_coeff helper · level 0 · unverified · e352afa5762c5a6b
  3. grl_hook update_rule · level 1 · ran · our draft was wrong · 9768efb52f591b55
  4. init_weights helper · level 0 · unverified · 7babf7ea472eba97

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 8 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. MADA entry · level 0 · unverified · e61d73732bf10468
  2. GRL helper · level 1 · ran · 3ce4eba45b4ca3fc
  3. load_backbone helper · level 1 · ran · our draft was wrong · f64f43c34c4542e9
  4. load_classifier helper · level 1 · ran · our draft was wrong · 8d9374ad6935ac3d
  5. linear2_bn helper · level 1 · ran · our draft was wrong · cd9167b485a751fd
  6. linear2_dr2_bn helper · level 1 · ran · our draft was wrong · 3e123903386d5131
  7. linear3_bn2_v1 helper · level 1 · ran · our draft was wrong · cec816fd8905007d
  8. linear3_bn2_v2 helper · level 1 · ran · our draft was wrong · 946555f6a21e149f

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 9 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. DANNtrainer entry · level 0 · unverified · b69e7e3bd38b5a79
  2. BaseDANNLike model · level 0 · unverified · 6ca780e6cedb8469
  3. Method helper · level 0 · unverified · c0ae116e1108bfcf
  4. ReverseLayerF helper · level 1 · ran · a9713d2fe23f5ada
  5. BaseAdaptTrainer helper · level 1 · ran · 0e5b0fea39063b16
  6. cross_entropy_logits loss · level 1 · ran; the contract check could not run (RAISES) · 310d54a1dd86ec79
  7. get_aggregated_metrics helper · level 1 · ran · our draft was wrong · 4113c2e807d432ee
  8. get_aggregated_metrics_from_dict helper · level 1 · ran · our draft was wrong · 61fd42a2e2a7cfcc
  9. get_metrics_from_parameter_dict helper · level 1 · ran · our draft was wrong · 704df3b8019c2aa5

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. domain_confusion entry · level 0 · unverified · 48ebff402229f303

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 6 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. train entry · level 0 · unverified · 1e5fb974a2b9088c
  2. batch_generator sampler · level 1 · ran · our draft was wrong · 4a9bc68de4ae0c55
  3. build_models model · level 1 · ran · our draft was wrong · f9776e8c18b947b6
  4. write_log helper · level 0 · unverified · 882f695d04b3d5b7
  5. alexnet helper · level 1 · ran · our draft was wrong · d86e29f3ca97a8c2
  6. vgg_16 helper · level 1 · ran · our draft was wrong · 851159feffea3b04

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FeatureExtractor entry · level 0 · unverified · 3d0632c955417561

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. Discriminator entry · level 1 · ran · 87db2131110dfd0a
  2. GradReverse helper · level 1 · ran · 22d411c2795ced15

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. DANNModel entry · level 0 · unverified · 9e554f3838a1af56
  2. ReverseLayerF helper · level 1 · ran · 917fb058e1f4bb05

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 4 bricks; individually on a fixture: 3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. DANN entry · level 0 · unverified · cd0abd234c0eba6b
  2. CellTypeCLF model · level 1 · ran · e2db8a3a21c6bf4c
  3. GradReverse model · level 1 · ran · 1a6a7062274a346d
  4. ResBlock helper · level 1 · ran · 1a8c0c365eb16cdc

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. AbstractDANN entry · level 1 · ran · 8a387c444dc4c6a4
  2. Algorithm helper · level 1 · ran · f4f62760b15a2f01

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. DANN entry · level 1 · ran · 59f8b8a3c0a6bdfe
  2. GradientReversalLayer helper · level 0 · unverified · a5f777ab36b3f81e

harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. DANN entry · level 0 · unverified · fcde4e5aa7af7696
  1. ClassifierBase · e8e9b56027129a67 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. AlexNetDANN · f06496e357b07abb · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. WANN · f2db1ef7274004c7 · 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. DANN · f679a4707e16e77e · 8 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. FlipGradientBuilder · f9923162a6acd1b6 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin

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="1505.07818") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain AdaptationDomain GeneralizationGeneral ClassificationImage ClassificationPerson Re-IdentificationRepresentation LearningSentiment AnalysisUnsupervised Domain Adaptationimage-classification

Datasets

Introduced by this paper, per the archive.

MNIST-M

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation MNIST-to-MNIST-M DANN [ganin2016domain] Accuracy 77.4 #4 of 5 Archive leaderboard report
Domain Adaptation SVNH-to-MNIST DANN [ganin2016domain] Accuracy 70.7 #9 of 9 Archive leaderboard report
Domain Adaptation Synth Digits-to-SVHN DANN [ganin2016domain] Accuracy 90.3 #2 of 4 Archive leaderboard report
Sentiment Analysis Multi-Domain Sentiment Dataset DANN Average 76.26 #6 of 6 Archive leaderboard report
Sentiment Analysis Multi-Domain Sentiment Dataset DANN Books 71.43 #6 of 6 Archive leaderboard report
Sentiment Analysis Multi-Domain Sentiment Dataset DANN DVD 75.4 #6 of 6 Archive leaderboard report
Sentiment Analysis Multi-Domain Sentiment Dataset DANN Electronics 77.67 #6 of 6 Archive leaderboard report
Sentiment Analysis Multi-Domain Sentiment Dataset DANN Kitchen 80.53 #6 of 6 Archive leaderboard report
Synthetic-to-Real Translation Syn2Real-C DANN Accuracy 57.4 #5 of 6 Archive leaderboard report
Unsupervised Domain Adaptation EPIC-KITCHENS-100 DANN Average Accuracy 39.2 #4 of 5 Archive leaderboard report
Unsupervised Domain Adaptation HMDB-UCF DANN Accuracy 88.09 #6 of 6 Archive leaderboard report
Unsupervised Domain Adaptation Jester (Gesture Recognition) DANN Accuracy 55.4 #4 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home DANN [cite:JMLR16RevGrad] Accuracy 76.8 #12 of 20 Archive leaderboard report
Unsupervised Domain Adaptation UCF-HMDB DANN Accuracy 80.83 #5 of 6 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