Papers › POEM: Polarization of Embeddings for Domain-Invariant Representations

POEM: Polarization of Embeddings for Domain-Invariant Representations

22 May 2023arXiv:2305.13046archive 2025-07-28

Sang-Yeong Jo, Sung Whan Yoon

Handling out-of-distribution samples is a long-lasting challenge for deep visual models. In particular, domain generalization (DG) is one of the most relevant tasks that aims to train a model with a generalization capability on novel domains. Most existing DG approaches share the same philosophy to minimize the discrepancy between domains by finding the domain-invariant representations. On the contrary, our proposed method called POEM acquires a strong DG capability by learning domain-invariant and domain-specific representations and polarizing them. Specifically, POEM cotrains category-classifying and domain-classifying embeddings while regularizing them to be orthogonal via minimizing the cosine-similarity between their features, i.e., the polarization of embeddings. The clear separation of embeddings suppresses domain-specific features in the domain-invariant embeddings. The concept of POEM shows a unique direction to enhance the domain robustness of representations that brings considerable and consistent performance gains when combined with existing DG methods. Extensive simulation results in popular DG benchmarks with the PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet datasets show that POEM indeed facilitates the category-classifying embedding to be more domain-invariant.

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="2305.13046")

Code

Syntology Ran 9 of 12 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

josangyoung/official-poem 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

12 samples harvested; 9 ran; 1 honoured the contract we drafted; 3 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
3ran · our draft was wrong
5ran
3unverified

Licence: 0 of the 12 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 JoSangYoung/Official-POEM. “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.

Classifier JoSangYoung/Official-POEM/POEM/domainbed/networks.py official repository ran · our draft was wrong MIT (permissive) · ce7990d7ad5821ff · report
conv3x3 JoSangYoung/Official-POEM/POEM/domainbed/lib/wide_resnet.py official repository ran · our draft was wrong MIT (permissive) · 00e569acd6b45ef0 · report
hashable JoSangYoung/Official-POEM/POEM/domainbed/lib/query.py official repository ran fingerprinted MIT (permissive) · 71a3a61ceed99bf3 · report
levelize JoSangYoung/Official-POEM/POEM/domainbed/lib/logger.py official repository ran fingerprinted MIT (permissive) · 2f597a2077a1c95d · report
make_selector_fn JoSangYoung/Official-POEM/POEM/domainbed/lib/query.py official repository ran MIT (permissive) · 2f8af5779e1edcb6 · report
make_weights_for_balanced_classes JoSangYoung/Official-POEM/POEM/domainbed/lib/misc.py official repository ran MIT (permissive) · 955c4020424d8ac1 · report
random_pairs_of_minibatches JoSangYoung/Official-POEM/POEM/domainbed/lib/misc.py official repository ran · our draft was wrong MIT (permissive) · 4fa2b54178fcc1df · report
to_minibatch JoSangYoung/Official-POEM/POEM/domainbed/algorithms/algorithms.py official repository ran · honoured contract fingerprinted MIT (permissive) · 12c23ce22097acd0 · report
to_row JoSangYoung/Official-POEM/POEM/domainbed/lib/misc.py official repository ran MIT (permissive) · 5dd6a674fbe45a89 · report
accuracy_from_loader JoSangYoung/Official-POEM/POEM/domainbed/evaluator.py official repository unverified MIT (permissive) · a62dd31d0dda9584 · report
default_hparams JoSangYoung/Official-POEM/POEM/domainbed/hparams_registry.py official repository unverified MIT (permissive) · dc2789597240a515 · report
random_hparams JoSangYoung/Official-POEM/POEM/domainbed/hparams_registry.py official repository unverified MIT (permissive) · 2bec6a705865507b · report

Tasks

Domain GeneralizationPhilosophy

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization DomainNet POEM Average Accuracy 44.0 #34 of 38 Archive leaderboard report
Domain Generalization Office-Home POEM Average Accuracy 68.0 #36 of 45 Archive leaderboard report
Domain Generalization PACS POEM Average Accuracy 86.7 #43 of 133 Archive leaderboard report
Domain Generalization TerraIncognita POEM Average Accuracy 49.5 #26 of 30 Archive leaderboard report
Domain Generalization VLCS POEM Average Accuracy 79.2 #27 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