Papers › Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

21 Mar 2022arXiv:2203.10789archive 2025-07-28

Junbum Cha, Kyungjae Lee, Sungrae Park, Sanghyuk Chun

Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains. Previous attempts to DG fail to learn domain-invariant representations only from the source domains due to the significant domain shifts between training and test domains. Instead, we re-formulate the DG objective using mutual information with the oracle model, a model generalized to any possible domain. We derive a tractable variational lower bound via approximating the oracle model by a pre-trained model, called Mutual Information Regularization with Oracle (MIRO). Our extensive experiments show that MIRO significantly improves the out-of-distribution performance. Furthermore, our scaling experiments show that the larger the scale of the pre-trained model, the greater the performance improvement of MIRO. Source code is available at https://github.com/kakaobrain/miro.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.10789")

Code

Syntology Ran 11 of 13 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kakaobrain/miro officialmentioned in papermentioned on GitHubpytorchMIT 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

13 samples harvested; 11 ran; 1 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
8ran
2unverified

Licence: 0 of the 13 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 kakaobrain/miro. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv3x3 kakaobrain/miro/domainbed/lib/wide_resnet.py official repository ran · our draft was wrong MIT (permissive) · 00e569acd6b45ef0 · report
default_hparams kakaobrain/miro/domainbed/hparams_registry.py official repository ran fingerprinted MIT (permissive) · 02a21c87d500ef9d · report
get_shapes kakaobrain/miro/domainbed/algorithms/miro.py official repository ran MIT (permissive) · c5919b96db289dbd · report
hashable kakaobrain/miro/domainbed/lib/query.py official repository ran fingerprinted MIT (permissive) · 71a3a61ceed99bf3 · report
levelize kakaobrain/miro/domainbed/lib/logger.py official repository ran fingerprinted MIT (permissive) · 2f597a2077a1c95d · report
make_selector_fn kakaobrain/miro/domainbed/lib/query.py official repository ran MIT (permissive) · 2f8af5779e1edcb6 · report
make_weights_for_balanced_classes kakaobrain/miro/domainbed/lib/misc.py official repository ran MIT (permissive) · 955c4020424d8ac1 · report
random_hparams kakaobrain/miro/domainbed/hparams_registry.py official repository ran MIT (permissive) · 58e06fd6cfa6a889 · report
random_pairs_of_minibatches kakaobrain/miro/domainbed/lib/misc.py official repository ran · our draft was wrong MIT (permissive) · 4fa2b54178fcc1df · report
to_minibatch kakaobrain/miro/domainbed/algorithms/algorithms.py official repository ran · honoured contract fingerprinted MIT (permissive) · 12c23ce22097acd0 · report
to_row kakaobrain/miro/domainbed/lib/misc.py official repository ran MIT (permissive) · 5dd6a674fbe45a89 · report
accuracy_from_loader kakaobrain/miro/domainbed/evaluator.py official repository unverified MIT (permissive) · 687efdf3db9c44df · report
get_writer kakaobrain/miro/domainbed/lib/writers.py official repository unverified MIT (permissive) · aa6558d41d5c4673 · report

Tasks

Domain Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization DomainNet MIRO (RegNetY-16GF, SWAD) Average Accuracy 60.7 #11 of 38 Archive leaderboard report
Domain Generalization DomainNet MIRO (ResNet-50, SWAD) Average Accuracy 47.0 #27 of 38 Archive leaderboard report
Domain Generalization Office-Home MIRO (RegNetY-16GF, SWAD) Average Accuracy 83.3 #12 of 45 Archive leaderboard report
Domain Generalization Office-Home MIRO (ResNet-50, SWAD) Average Accuracy 72.4 #25 of 45 Archive leaderboard report
Domain Generalization PACS MIRO (RegNetY-16GF, SWAD) Average Accuracy 96.8 #9 of 133 Archive leaderboard report
Domain Generalization PACS MIRO (ResNet-50, SWAD) Average Accuracy 88.4 #28 of 133 Archive leaderboard report
Domain Generalization TerraIncognita MIRO (RegNetY-16GF, SWAD) Average Accuracy 64.3 #3 of 30 Archive leaderboard report
Domain Generalization TerraIncognita MIRO (ResNet-50, SWAD) Average Accuracy 52.9 #16 of 30 Archive leaderboard report
Domain Generalization VLCS MIRO (RegNetY-16GF, SWAD) Average Accuracy 81.7 #16 of 37 Archive leaderboard report
Domain Generalization VLCS MIRO (ResNet-50, SWAD) Average Accuracy 79.6 #24 of 37 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