Papers › Universal Representation Learning from Multiple Domains for Few-shot Classification

Universal Representation Learning from Multiple Domains for Few-shot Classification

25 Mar 2021ICCV 2021 10arXiv:2103.13841archive 2025-07-28

Wei-Hong Li, Xialei Liu, Hakan Bilen

In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods use adaptation networks for aligning their features to new domains or select the relevant features from multiple domain-specific feature extractors. In this work, we propose to learn a single set of universal deep representations by distilling knowledge of multiple separately trained networks after co-aligning their features with the help of adapters and centered kernel alignment. We show that the universal representations can be further refined for previously unseen domains by an efficient adaptation step in a similar spirit to distance learning methods. We rigorously evaluate our model in the recent Meta-Dataset benchmark and demonstrate that it significantly outperforms the previous methods while being more efficient. Our code will be available at https://github.com/VICO-UoE/URL.

PaperPDFConference PDFCodeCode 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="2103.13841")

Code

Syntology Ran 12 of 26 code samples harvested from 4 repositories linked to this paper; 14 have no recorded run. Of those that ran: 11 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 25 samples from 3 repositories, 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.

VICO-UoE/URL officialmentioned in papermentioned on GitHubtf report
google-research/meta-dataset officialmentioned in papermentioned on GitHubtf report
tmlr-group/CoPA mentioned on GitHubtf report
tmlr-group/mokd mentioned on GitHubtfMIT report
vico-uoe/universalrepresentations mentioned on GitHubpytorch 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

26 samples harvested; 12 ran; 0 honoured the contract we drafted; 14 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.

11ran · our draft was wrong
1ran
14unverified

Licence: 0 of the 26 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 4 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.

pa VICO-UoE/URL/models/tsa.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 8f26f9f0da493c06 · report
apply_selection tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 7e968a05de2ba8b3 · report
centering tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 122da5c3e4363856 · report
compute_avg_prototypes tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · fa075e62a49c4713 · report
compute_max_prototype tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · bfdceee8e94ba8ee · report
compute_most_sim_prototype tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 7bc0c018da29b173 · report
compute_sum_prototype tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 8c6dd9a5516475ee · report
cross_entropy_loss tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · ab00127e0e9d1905 · report
kernel_CKA tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b1de118bad80d84f · report
kernel_HSIC tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c1fa4a28c0967388 · report
prototype_loss tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 3e380e81bdaa50cd · report
rbf tmlr-group/CoPA/models/pa.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · ad1380889172ec1f · report
ResNet vico-uoe/universalrepresentations/VisualDecathlon/models.py community (archive-listed) unverified MIT (permissive) · ffad41c1ddd8d6c1 · report
cal_dist tmlr-group/mokd/models/losses.py community (archive-listed) unverified MIT (permissive) · 68e3d9ea3b5a4b42 · report
cal_dist_cosine tmlr-group/mokd/models/losses.py community (archive-listed) unverified MIT (permissive) · 1700ff73ab4e452a · report
compute_prototypes tmlr-group/mokd/hsic_loss.py community (archive-listed) unverified MIT (permissive) · fad178676f5c5101 · report
cosine_sim tmlr-group/mokd/models/model_utils.py community (archive-listed) unverified MIT (permissive) · 28cc87a06ba68afb · report
get_optimizer tmlr-group/mokd/models/model_helpers.py community (archive-listed) unverified MIT (permissive) · 94d7d1aa90bc2d6f · report
imq tmlr-group/mokd/models/hsic_estimation.py community (archive-listed) unverified MIT (permissive) · d2e93fa24f8623c1 · report
labels_to_episode_labels tmlr-group/mokd/models/model_utils.py community (archive-listed) unverified MIT (permissive) · 42107d08a8a749ec · report
linear tmlr-group/mokd/models/hsic_estimation.py community (archive-listed) unverified MIT (permissive) · dd2fbf6ed2260eae · report
linear_HSIC tmlr-group/mokd/models/cka.py community (archive-listed) unverified MIT (permissive) · 78c17a9df7b56d4d · report
pa tmlr-group/CoPA/models/pa.py community (archive-listed) unverified MIT (permissive) · 3990fde51995b22c · report
pred_with_protos tmlr-group/mokd/hsic_loss.py community (archive-listed) unverified MIT (permissive) · 549d8369236aee08 · report
rbf tmlr-group/mokd/models/cka.py community (archive-listed) unverified MIT (permissive) · 1dddaffd3ae4142f · report
rbf tmlr-group/mokd/models/hsic_estimation.py community (archive-listed) unverified MIT (permissive) · 29877c45faa57d6f · report

Tasks

ClassificationFew-Shot Image ClassificationGeneral ClassificationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Meta-Dataset URL (ResNet18, 84x84 image, shuffled data, scratch, MDL) Accuracy 75.75 #6 of 22 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