Papers › Adversarial Discriminative Domain Adaptation
Adversarial Discriminative Domain Adaptation
Eric Tzeng, Judy Hoffman, Kate Saenko, Trevor Darrell
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial approaches to unsupervised domain adaptation have recently been introduced, which reduce the difference between the training and test domain distributions and thus improve generalization performance. Prior generative approaches show compelling visualizations, but are not optimal on discriminative tasks and can be limited to smaller shifts. Prior discriminative approaches could handle larger domain shifts, but imposed tied weights on the model and did not exploit a GAN-based loss. We first outline a novel generalized framework for adversarial adaptation, which subsumes recent state-of-the-art approaches as special cases, and we use this generalized view to better relate the prior approaches. We propose a previously unexplored instance of our general framework which combines discriminative modeling, untied weight sharing, and a GAN loss, which we call Adversarial Discriminative Domain Adaptation (ADDA). We show that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and demonstrate the promise of our approach by exceeding state-of-the-art unsupervised adaptation results on standard cross-domain digit classification tasks and a new more difficult cross-modality object classification task.
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="1702.05464")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1702.05464", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1702.05464")
Code
Syntology 48 code samples harvested from 14 repositories linked to this paper: 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. Where Syntology's instrument failed: 6 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): 48 samples from 14 repositories, 14 ran (7 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- antoinedemathelin/wann, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
20 repositories listed; official and paper-mentioned ones first.
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
48 samples harvested: 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. “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.
Licence: 12 of the 48 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 14 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
084dfb3d87216615 · report
fixture: returned tuple · level recorded 2026-09-22 8834a2ebbe444d53 · report
fixture: returned Discriminator · level recorded 2026-09-22 e8e38bfc623d704e · report
fixture: returned Discriminator · level recorded 2026-09-22 dfe3c0d123bc7830 · report
fixture: signature network:callable/0/?, copy:bool/0/bool, name:str/0/str, force_copy:bool/0/bool · returned Functional · level recorded 2026-09-22 60cfae1e4c765da8 · report
fixture: signature name:str/0/str, state:int/0/int · returned Sequential · level recorded 2026-09-22 ba83013d36128386 · report
fixture: signature name:str/0/str, state:int/0/int · returned Sequential · level recorded 2026-09-22 4078865962ffaf59 · report
fixture: signature activation:str/0/str, name:str/0/str, state:int/0/int · returned Sequential · level recorded 2026-09-22 91edb2b8f17a72f6 · report
bfd00c4055fd2adc · report
fixture: returned tfADDA · level recorded 2026-09-22 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input models.py unverified MIT (permissive) ·
12ddf95e9fccb3c4 · report
a382b74025c113e5 · report
566bf3a9068aa745 · report
4c5ddb71c68be51a · report
fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22 af8de7283d2b0b9e · report
fixture: signature iterable:list/1/int · returned generator · level recorded 2026-09-22 ebf44e526ae75e68 · report
fixture: returned Discriminator · level recorded 2026-09-22 7bb28fb79002a53d · report
fixture: signature domain_pred:Tensor/1/float, domain_label:str/0/str · returned Tensor · level recorded 2026-09-24 622c3f05a9b70b22 · report
fixture: signature x:dict/0/?, prefix:str/0/str, suffix:str/0/str · returned dict · level recorded 2026-09-22 4b4ebf6d67718656 · report
2607dc161f092df7 · report
f4f0abb8e8238039 · report
040844c8bd2ffcae · report
ba9568d0ea5cbcee · report
ad7cd588e5081b5d · report
72b333545ead7d03 · report
724735f6d9545589 · report
ff6a75be2bbdf375 · report
7cbe490d83bf8263 · report
2a961204ae724b34 · report
7ee0559533467085 · report
fixture: returned Discriminator · level recorded 2026-09-22 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.
14 assemblies on this paper: 14 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
14 sibling assemblies for Adversarial Discriminative Domain Adaptation (ADDA) (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 14 sibling assemblies; the other 2 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 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.
one of 14 siblings
- DomainAdversarialLoss entry · level 1 · ran ·
7bb28fb79002a53d
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 1 brick; 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) · 0 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 14 siblings
- Discriminator entry · level 1 · ran ·
7ee0559533467085
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- concat_ad_loss_2 entry · level 0 · unverified ·
a382b74025c113e5 - discriminator model · level 0 · unverified ·
566bf3a9068aa745
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 2 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- train_tgt entry · level 0 · unverified ·
b2531ab289d6f8e9 - make_variable helper · level 1 · ran · our draft was wrong ·
3714824fc72387d9
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 1 brick; 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) · 0 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 14 siblings
- Discriminator entry · level 1 · ran ·
8834a2ebbe444d53
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- train_tgt entry · level 0 · unverified ·
8ab9e937c7ff7cd1 - make_cuda helper · level 1 · ran · honoured contract ·
4c5ddb71c68be51a
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 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 14 siblings
- tfADDA entry · level 1 · ran ·
bfd00c4055fd2adc - swish helper · level 0 · unverified ·
12ddf95e9fccb3c4
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 15 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- ADDA entry · level 0 · unverified ·
ce9e1a5eac1050da - BaseAdaptDeep helper · level 0 · unverified ·
91edb2b8f17a72f6 - check_network helper · level 1 · ran · our draft was wrong ·
dfe3c0d123bc7830 - make_insert_doc helper · level 1 · ran · our draft was wrong ·
337c118be78fa411 - BaseAdapt helper · level 0 · unverified ·
cf4b39f677292095 - accuracy helper · level 1 · ran · honoured contract ·
9914f5b3194c1f7b - check_arrays helper · level 1 · ran · honoured contract ·
b28b2fd06d28b0a0 - check_if_compiled helper · level 1 · ran · violated contract ·
8845995e56d4cff9 - get_default_discriminator helper · level 1 · ran · our draft was wrong ·
60cfae1e4c765da8 - get_default_encoder helper · level 1 · ran · our draft was wrong ·
ba83013d36128386 - get_default_task helper · level 1 · ran · our draft was wrong ·
4078865962ffaf59 - set_random_seed helper · level 0 · unverified ·
988358e38ca0a57c - check_sample_weight helper · level 1 · ran; the contract check could not run ·
753fda05a9c00a3e - normalized_linear_discrepancy helper · level 1 · ran; the contract check could not run ·
80f788d717b43cf5 - linear_discrepancy helper · level 1 · ran; the contract check could not run ·
5ee018c7b767d60e
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 23 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 22 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- ADDAHook entry · level 0 · unverified ·
25e34a726b2ba605 - ChainHook helper · level 0 · unverified ·
46a87df5beca7a35 - EmptyHook helper · level 0 · unverified ·
97400f2418c74bce - FalseHook helper · level 0 · unverified ·
31542fd54d3ac9ac - FeaturesHook helper · level 0 · unverified ·
ad7cd588e5081b5d - FeaturesWithGradAndDetachedHook helper · level 0 · unverified ·
72b333545ead7d03 - FrozenModelHook helper · level 0 · unverified ·
724735f6d9545589 - GANHook helper · level 0 · unverified ·
3bf49b3d9b8d635e - StrongDHook helper · level 0 · unverified ·
08838ca55f39ac9f - TrueHook helper · level 0 · unverified ·
40469ce9b9b8e75d - BaseConditionHook helper · level 0 · unverified ·
4b4ebf6d67718656 - BaseHook helper · level 0 · unverified ·
ca7d95b46428e282 - ZeroLossHook helper · level 0 · unverified ·
ff6a75be2bbdf375 - BaseFeaturesHook helper · level 0 · unverified ·
2607dc161f092df7 - BaseWrapperHook helper · level 0 · unverified ·
f4f0abb8e8238039 - CLossHook helper · level 0 · unverified ·
f4b49872d61ca7cb - DLogitsHook helper · level 0 · unverified ·
433003a2c8fc7f61 - FeaturesChainHook helper · level 0 · unverified ·
ba9568d0ea5cbcee - check_keys_are_present helper · level 0 · unverified ·
7cbe490d83bf8263 - replace_mapped_keys helper · level 0 · unverified ·
2a961204ae724b34 - wrap_keys helper · level 1 · ran · our draft was wrong ·
622c3f05a9b70b22 - FeaturesAndLogitsHook helper · level 0 · unverified ·
040844c8bd2ffcae - LogitsHook helper · level 0 · unverified ·
4bd3dad9e4078393
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 1 brick; 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) · 0 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 14 siblings
- Discriminator entry · level 1 · ran ·
e8e38bfc623d704e
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 14 siblings
- train_tgt entry · level 0 · unverified ·
84d421fc6e4a0800 - eval_src metric · level 0 · unverified ·
ae0275061ef16144 - make_cuda helper · level 1 · ran · honoured contract ·
4c5ddb71c68be51a - mixup_data helper · level 1 · ran; the contract check could not run (RAISES) ·
084dfb3d87216615
harvested Assembly for Adversarial Discriminative Domain Adaptation (ADDA) (graph method: Adversarial Discriminative Domain Adaptation (ADDA)). 1 brick; 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) · 0 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 14 siblings
- Discriminator entry · level 1 · ran ·
ebf44e526ae75e68
- main · 8b153857663da8ce · 7 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- train_tgt · acb1d3d98f68a0ab · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[13] 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="1702.05464") 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 |
|---|---|---|---|---|---|---|---|
| Domain Adaptation | MNIST-to-USPS | ADDN | Accuracy | 90.1 | #14 of 14 | Archive leaderboard | report |
| Domain Adaptation | SVHN-to-MNIST | ADDN | Accuracy | 80.1 | #13 of 14 | Archive leaderboard | report |
| Unsupervised Domain Adaptation | EPIC-KITCHENS-100 | ADDA | Average Accuracy | 37.4 | #5 of 5 | Archive leaderboard | report |
| Unsupervised Domain Adaptation | HMDB-UCF | ADDA | Accuracy | 88.44 | #5 of 6 | Archive leaderboard | report |
| Unsupervised Domain Adaptation | Jester (Gesture Recognition) | ADDA | Accuracy | 52.3 | #5 of 5 | Archive leaderboard | report |
| Unsupervised Domain Adaptation | UCF-HMDB | ADDA | Accuracy | 79.17 | #6 of 6 | Archive leaderboard | report |
| Unsupervised Image-To-Image Translation | SVNH-to-MNIST | ADDA | Classification Accuracy | 76.0% | #3 of 4 | 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
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