Papers › Deeper, Broader and Artier Domain Generalization

Deeper, Broader and Artier Domain Generalization

9 Oct 2017ICCV 2017 10arXiv:1710.03077archive 2025-07-28

Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training. For example recognition in sketch images, which are distinctly more abstract and rarer than photos. Nevertheless, DG methods have primarily been evaluated on photo-only benchmarks focusing on alleviating the dataset bias where both problems of domain distinctiveness and data sparsity can be minimal. We argue that these benchmarks are overly straightforward, and show that simple deep learning baselines perform surprisingly well on them. In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning. Secondly, we develop a DG benchmark dataset covering photo, sketch, cartoon and painting domains. This is both more practically relevant, and harder (bigger domain shift) than existing benchmarks. The results show that our method outperforms existing DG alternatives, and our dataset provides a more significant DG challenge to drive future research.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1710.03077")

Code

Syntology Ran 3 of 7 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Evgeneus/Graph-Domain-Adaptaion mentioned on GitHubpytorch report
deeplearning-wisc/hypo mentioned on GitHubpytorch report
facebookresearch/DomainBed mentioned on GitHubpytorch report
facebookresearch/ModelRatatouille mentioned on GitHubpytorch report
hlzhang109/ddg mentioned on GitHubpytorch report
xch-liu/geom-tex-dg mentioned 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

7 samples harvested; 3 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
4unverified

Licence: 0 of the 7 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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 xch-liu/geom-tex-dg/Dassl/dassl/modeling/backbone/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_test_records hlzhang109/ddg/model_selection.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 53fac8d8d949e72b · report
stage_path hlzhang109/ddg/scripts/download.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c631ff42fed59f21 · report
compute_accuracy xch-liu/geom-tex-dg/Dassl/dassl/metrics/accuracy.py community (archive-listed) unverified MIT (permissive) · da48cf51668411a0 · report
compute_distance_matrix xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py community (archive-listed) unverified MIT (permissive) · cbff6e3d6b3109ac · report
cosine_distance xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py community (archive-listed) unverified MIT (permissive) · e8878931ade705ee · report
euclidean_squared_distance xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py community (archive-listed) unverified MIT (permissive) · 4dae6b1e21e10987 · report

Tasks

Domain Generalization

Datasets

Introduced by this paper, per the archive.

PACS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization PACS TF (Alexnet) Average Accuracy 69.21 #127 of 133 Archive leaderboard report
Domain Generalization PACS LRE-SVM Average Accuracy 58.99 #130 of 133 Archive leaderboard report
Domain Generalization PACS SVM Average Accuracy 58.74 #131 of 133 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