Papers › Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

6 Jun 2020arXiv:2006.03806archive 2025-07-28

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive settings). Using standardized vision benchmarks, we prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

PaperPDFCodeCode Syntology ran

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 5 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 23 samples from 4 repositories, 19 ran (13 with no instrument failure; 6 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.

yhu01/PT-MAP officialmentioned in paperpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
allenhaozhu/ease mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
mbonto/fewshot_neuroimaging_classification mentioned on GitHubpytorchMITSyntology: 15 samples, 14 ran (2 instrument-failed) · 1 unverified report
xiangyu8/PT-MAP-sf mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
yhu01/bms mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
sicara/easy-few-shot-learning pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified), Laplacian Regularized Few-Shot Learning (arXiv:2006.15486; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified) and Transductive Information Maximization For Few-Shot Learning (arXiv:2008.11297; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 4 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.

1ran · honoured contract
6ran · our draft was wrong
3ran; the contract check could not run
12ran
4unverified

Licence: 12 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 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.

yhu01/PT-MAP official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
QRreduction test_standard.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c2a29a7f0baf902f · report fixture: signature datas:Tensor/3/float · returned Tensor · level recorded 2026-09-22
centerDatas test_standard.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · c317909266ed4d67 · report fixture: signature datas:Tensor/3/float · returned Tensor · level recorded 2026-09-22
scaleEachUnitaryDatas test_standard.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7bf4f43bdbd661d4 · report fixture: signature datas:Tensor/3/float · returned Tensor · level recorded 2026-09-22
allenhaozhu/ease community (archive-listed) 3 samples, 0 ran · 3 unverified
ClassesInRun FSLTask.py unverified no licence file found · pointer only · 9ae865b05537face · report
GenerateRun FSLTask.py unverified no licence file found · pointer only · a60c716cc71e54f7 · report
GenerateRunSet FSLTask.py unverified no licence file found · pointer only · 56ad4643b6fbdddd · report
mbonto/fewshot_neuroimaging_classification community (archive-listed) 15 samples, 14 ran (2 instrument-failed) · 1 unverified
augment_image in 12 papers MAML_plus_plus/data.py ran MIT (permissive) · 18f856fdae4a4061 · report fixture: signature image:ndarray/3/float, k:int/0/int, channels:int/0/int, augment_bool:bool/0/bool, args:dict/0/?, dataset_name:str/0/str · returned Tensor · level recorded 2026-09-24
batch_shape SimpleShot/functions.py ran MIT (permissive) · c160c8210094d8c7 · report fixture: signature model_name:str/0/str, x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
centerDatas SimpleShot/PT_plus_MAP.py ran fingerprinted MIT (permissive) · 1586cba5790084af · report fixture: signature datas:Tensor/3/float, n_lsamples:int/0/int · returned Tensor · level recorded 2026-09-24
compute_accuracy in 81 papers SimpleShot/functions.py ran MIT (permissive) · a280c947612b8a09 · report fixture: signature outputs:Tensor/2/float, y:Tensor/1/int · returned int · level recorded 2026-09-24
compute_normalized_adjacency MAML_plus_plus/meta_neural_network_architectures.py ran MIT (permissive) · aa05f8300c098828 · report fixture: signature adj_matrix:ndarray/2/float, threshold:bool/0/bool · returned Tensor · level recorded 2026-09-24
extract_top_level_dict in 7 papers MAML_plus_plus/meta_neural_network_architectures.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e6cee89c00846aec · report fixture: signature current_dict:dict/0/? · returned dict · level recorded 2026-09-22
fill_template in 8 papers MAML_plus_plus/script_generation_tools/generate_scripts.py ran MIT (permissive) · d25adfe464700ae6 · report fixture: signature template_list:list/1/str, execution_script:str/0/str, experiment_config:str/0/str · returned str · level recorded 2026-09-24
generate_combinations in 6 papers MAML_plus_plus/script_generation_tools/generate_configs.py ran MIT (permissive) · 2f7232018db3fa2e · report fixture: signature config:config/1/list · returned list · level recorded 2026-09-24
get_transforms_for_dataset MAML_plus_plus/data.py ran MIT (permissive) · 40f79117fc32f74c · report fixture: signature dataset_name:str/0/str, args:dict/0/?, k:int/0/int · returned tuple · level recorded 2026-09-24
load_template in 8 papers MAML_plus_plus/script_generation_tools/generate_configs.py ran MIT (permissive) · 27fabd65989ead1f · report fixture: signature filepath:str/0/str · returned str · level recorded 2026-09-24
load_template in 8 papers MAML_plus_plus/script_generation_tools/generate_scripts.py ran MIT (permissive) · 4a41646d1d2da5a6 · report fixture: signature filepath:str/0/str · returned list · level recorded 2026-09-24
propagation MAML_plus_plus/meta_neural_network_architectures.py ran fingerprinted MIT (permissive) · 0e4987f8a7cbc4cb · report fixture: signature features:Tensor/2/float, graph:Tensor/2/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
set_torch_seed in 7 papers MAML_plus_plus/few_shot_learning_system.py ran · our draft was wrong MIT (permissive) · 5c44538154dad8a7 · report fixture: signature seed:int/0/int · returned RandomState · level recorded 2026-09-22
train in 522 papers SimpleShot/functions.py ran MIT (permissive) · d5f7aba697839f38 · report fixture: signature model:callable/0/?, criterion:callable/0/?, optimizer:SGD/0/?, data_loader:list/1/tuple, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-24
fill_template in 8 papers MAML_plus_plus/script_generation_tools/generate_configs.py unverified MIT (permissive) · 6ef99887903cd30a · report
xiangyu8/PT-MAP-sf community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
train_manifold_mixup train_dct.py ran · our draft was wrong no licence file found · pointer only · 16aa65e2f94bd50a · report fixture: signature base_loader:list/1/tuple, base_loader_test:list/1/tuple, model:callable/0/?, start_epoch:int/0/int, stop_epoch:int/0/int, params:Params/0/? · returned ManifoldMixupModel · level recorded 2026-09-22
train_rotation train_dct.py ran · our draft was wrong no licence file found · pointer only · 085fb3f0b676ad6a · report fixture: signature base_loader:list/1/tuple, base_loader_test:list/1/tuple, model:callable/0/?, start_epoch:int/0/int, stop_epoch:int/0/int, params:ParamsConfig/0/?, tmp:dict/0/? · returned MinimalModel · level recorded 2026-09-22
yhu01/bms community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
centerDatas test_standard_bms.py ran · honoured contract fingerprinted no licence file found · pointer only · 600b828ba2526da0 · report fixture: signature datas:Tensor/2/float · returned Tensor · level recorded 2026-09-22
load_pickle in 115 papers test_standard_bms.py ran · our draft was wrong no licence file found · pointer only · 3fffadb9535ea4c6 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-22
reloadRuns test_standard_bms.py ran · our draft was wrong no licence file found · pointer only · ca2929dfbe4faf3e · report fixture: signature shot:int/0/int, n_ways:int/0/int, n_queries:int/0/int, n_runs:int/0/int · returned tuple · level recorded 2026-09-22

Tasks

Few-Shot Image ClassificationFew-Shot LearningGeneral Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) PT+MAP Accuracy 87.69 #6 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) PT+MAP Accuracy 90.68 #8 of 39 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 1-shot PT+MAP Accuracy 91.55% #8 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot PT+MAP Accuracy 93.99 #8 of 32 Archive leaderboard report
Few-Shot Image Classification Dirichlet CUB-200 (5-way, 1-shot) PT-MAP 1:1 Accuracy 65.1 #8 of 8 Archive leaderboard report
Few-Shot Image Classification Dirichlet CUB-200 (5-way, 5-shot) PT-MAP 1:1 Accuracy 71.3 #8 of 8 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 1-shot) PT-MAP 1:1 Accuracy 60.6 #6 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 5-shot) PT-MAP 1:1 Accuracy 67.1 #10 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 1-shot) PT-MAP 1:1 Accuracy 64.1 #8 of 9 Archive leaderboard report
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 5-shot) PT-MAP 1:1 Accuracy 70.0 #9 of 9 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning PT+MAP Accuracy 82.92% #1 of 16 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) PT+MAP Accuracy 62.49 #3 of 12 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (5-shot) PT+MAP Accuracy 76.51 #3 of 8 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) PT+MAP (transductive) Accuracy 82.92 #12 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (10-shot) PT+MAP Accuracy 90.03 #1 of 5 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) PT+MAP Accuracy 88.82 #15 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) PT+MAP Accuracy 85.41 #4 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) PT+MAP Accuracy 90.44 #5 of 51 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