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 ranMethod as code

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):

Code

Syntology 26 code samples harvested from 4 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 25 samples from 3 repositories, 19 ran (8 with no instrument failure; 11 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:

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.

VICO-UoE/URL officialmentioned in papermentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
google-research/meta-dataset officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (arXiv:1903.03096; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
tmlr-group/CoPA mentioned on GitHubtfSyntology: 12 samples, 11 ran (11 instrument-failed) · 1 unverified report
tmlr-group/mokd mentioned on GitHubtfMITSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 unverified report
vico-uoe/universalrepresentations mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified 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.

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

26 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 11 where Syntology's instrument failed) · 6 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.

11ran · our draft was wrong
9ran
6unverified

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; 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.

VICO-UoE/URL official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
pa models/tsa.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 8f26f9f0da493c06 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
tmlr-group/CoPA community (archive-listed) 12 samples, 11 ran (11 instrument-failed) · 1 unverified
apply_selection models/pa.py ran · our draft was wrong MIT (permissive) · 7e968a05de2ba8b3 · report fixture: signature features:Tensor/4/float, vartheta:list/1/Tensor · returned Tensor · level recorded 2026-09-22
centering in 17 papers models/pa.py ran · our draft was wrong MIT (permissive) · 122da5c3e4363856 · report fixture: returned Tensor · level recorded 2026-09-22
compute_avg_prototypes models/pa.py ran · our draft was wrong fingerprinted MIT (permissive) · fa075e62a49c4713 · report fixture: signature embeddings:Tensor/4/float, labels:Tensor/1/int, is_flatten:bool/0/bool · returned Tensor · level recorded 2026-09-22
compute_max_prototype models/pa.py ran · our draft was wrong fingerprinted MIT (permissive) · bfdceee8e94ba8ee · report fixture: signature embeddings:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
compute_most_sim_prototype models/pa.py ran · our draft was wrong fingerprinted MIT (permissive) · 7bc0c018da29b173 · report fixture: signature embeddings:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
compute_sum_prototype models/pa.py ran · our draft was wrong fingerprinted MIT (permissive) · 8c6dd9a5516475ee · report fixture: signature embeddings:Tensor/2/float, labels:Tensor/1/int, is_flatten:bool/0/bool · returned Tensor · level recorded 2026-09-22
cross_entropy_loss in 58 papers models/pa.py ran · our draft was wrong MIT (permissive) · ab00127e0e9d1905 · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/float · returned tuple · level recorded 2026-09-22
kernel_CKA models/pa.py ran · our draft was wrong MIT (permissive) · b1de118bad80d84f · report fixture: returned Tensor · level recorded 2026-09-22
kernel_HSIC in 9 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/pa.py ran · our draft was wrong MIT (permissive) · c1fa4a28c0967388 · report fixture: returned Tensor · level recorded 2026-09-22
prototype_loss in 5 papers models/pa.py ran · our draft was wrong MIT (permissive) · 3e380e81bdaa50cd · report fixture: signature support_embeddings:Tensor/2/float, support_labels:Tensor/1/int, query_embeddings:Tensor/2/float, query_labels:Tensor/1/int, distance:str/0/str, prot_type:str/0/str · returned tuple · level recorded 2026-09-22
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
models/pa.py ran · our draft was wrong fingerprinted MIT (permissive) · ad1380889172ec1f · report fixture: signature X:Tensor/2/float, sigma:NoneType/0/? · returned Tensor · level recorded 2026-09-22
pa models/pa.py unverified MIT (permissive) · 3990fde51995b22c · report
tmlr-group/mokd community (archive-listed) 12 samples, 8 ran (0 instrument-failed) · 4 unverified
cal_dist models/losses.py ran fingerprinted MIT (permissive) · 68e3d9ea3b5a4b42 · report fixture: signature inputs:Tensor/2/float, inputs_center:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_optimizer in 228 papers models/model_helpers.py ran MIT (permissive) · 94d7d1aa90bc2d6f · report fixture: signature model:callable/0/?, args:dict/0/?, params:NoneType/0/? · returned Adam · level recorded 2026-09-24
imq models/hsic_estimation.py ran fingerprinted MIT (permissive) · d2e93fa24f8623c1 · report fixture: signature X:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24
labels_to_episode_labels models/model_utils.py ran fingerprinted MIT (permissive) · 42107d08a8a749ec · report fixture: signature labels:Tensor/1/int · returned Tensor · level recorded 2026-09-24
linear in 88 papers models/hsic_estimation.py ran fingerprinted MIT (permissive) · dd2fbf6ed2260eae · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-24
linear_HSIC models/cka.py ran fingerprinted MIT (permissive) · 78c17a9df7b56d4d · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
models/cka.py ran fingerprinted MIT (permissive) · 1dddaffd3ae4142f · report fixture: signature X:Tensor/2/float, sigma:NoneType/0/? · returned Tensor · level recorded 2026-09-24
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
models/hsic_estimation.py ran MIT (permissive) · 29877c45faa57d6f · report fixture: signature X:Tensor/2/float, stat_mode:str/0/str, scale:Tensor/0/float, q_quantile:float/0/float · returned Tensor · level recorded 2026-09-24
cal_dist_cosine models/losses.py unverified MIT (permissive) · 1700ff73ab4e452a · report
compute_prototypes in 7 papers hsic_loss.py unverified MIT (permissive) · fad178676f5c5101 · report
cosine_sim in 34 papers models/model_utils.py unverified MIT (permissive) · 28cc87a06ba68afb · report
pred_with_protos hsic_loss.py unverified MIT (permissive) · 549d8369236aee08 · report
vico-uoe/universalrepresentations community (archive-listed) 1 sample, 0 ran · 1 unverified
ResNet in 139 papers VisualDecathlon/models.py unverified MIT (permissive) · ffad41c1ddd8d6c1 · report

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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for URL (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for URL (graph method: URL). 12 bricks; individually on a fixture: 11 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; 11 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. pa entry · level 0 · unverified · 3990fde51995b22c
  2. apply_selection helper · level 1 · ran · our draft was wrong · 7e968a05de2ba8b3
  3. prototype_loss helper · level 1 · ran · our draft was wrong · 3e380e81bdaa50cd
  4. compute_avg_prototypes helper · level 1 · ran · our draft was wrong · fa075e62a49c4713
  5. compute_max_prototype helper · level 1 · ran · our draft was wrong · bfdceee8e94ba8ee
  6. compute_most_sim_prototype helper · level 1 · ran · our draft was wrong · 7bc0c018da29b173
  7. compute_sum_prototype helper · level 1 · ran · our draft was wrong · 8c6dd9a5516475ee
  8. cross_entropy_loss helper · level 1 · ran · our draft was wrong · ab00127e0e9d1905
  9. kernel_CKA helper · level 1 · ran · our draft was wrong · b1de118bad80d84f
  10. kernel_HSIC helper · level 1 · ran · our draft was wrong · c1fa4a28c0967388
  11. centering helper · level 1 · ran · our draft was wrong · 122da5c3e4363856
  12. rbf helper · level 1 · ran · our draft was wrong · ad1380889172ec1f

harvested Assembly for URL (graph method: URL). 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 3 siblings

  1. pa entry · level 1 · ran · 8f26f9f0da493c06

harvested Assembly for URL (graph method: URL). 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 3 siblings

  1. ResNet entry · level 0 · unverified · ffad41c1ddd8d6c1
  2. conv3x3 helper · level 1 · ran · our draft was wrong · 583f9780bdd00a45

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="2103.13841") returns these assemblies with each brick's role and wiring (how to connect).

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