Papers › Matching Networks for One Shot Learning

Matching Networks for One Shot Learning

13 Jun 2016NeurIPS 2016 12arXiv:1606.04080archive 2025-07-28

Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra

Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new concepts rapidly from little data. In this work, we employ ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories. Our framework learns a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. We then define one-shot learning problems on vision (using Omniglot, ImageNet) and language tasks. Our algorithm improves one-shot accuracy on ImageNet from 87.6% to 93.2% and from 88.0% to 93.8% on Omniglot compared to competing approaches. We also demonstrate the usefulness of the same model on language modeling by introducing a one-shot task on the Penn Treebank.

PaperPDFConference PDFCodeCode 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 16 code samples harvested from 5 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 16 samples from 5 repositories, 11 ran (5 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

26 repositories listed; official and paper-mentioned ones first.

AntreasAntoniou/MatchingNetworks mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
KamalM8/Few-Shot-learning-Fashion mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
LiuXinyu12378/MatchingNetworks mentioned on GitHubtfMITSyntology: not harvested report
RajeevReddyIlavala/Low-Shot-Learning-Learning mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
SeonbeomKim/TensorFlow-Matching_Networks_for_One_Shot_Learning mentioned on GitHubtfSyntology: not harvested report
Sha-Lab/FEAT mentioned on GitHubpytorchSyntology: 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); nothing checks that they implement this paper's method. report
WenbinLee/DN4 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
adriangonz/statistical-nlp-17 mentioned on GitHubpytorchSyntology: not harvested report
cnichkawde/MatchingNetwork mentioned on GitHubSyntology: not harvested report
cnielly/prototypical-networks-omniglot mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/low-shot-shrink-hallucinate mentioned on GitHubpytorchSyntology: 6 samples, 3 ran (3 instrument-failed) · 3 unverified report
fiveai/on-episodes-fsl mentioned on GitHubpytorchSyntology: not harvested report
fujenchu/matchingNet mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
hrdwsong/ProtoNet-Paddle mentioned on GitHubpaddleSyntology: not harvested report
knnaraghi/fewshot mentioned on GitHubtfSyntology: not harvested report
oscarknagg/few-shot mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified) and 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); nothing checks that they implement this paper's method. report
qitianwu/nodeformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification (arXiv:2306.08385; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
sambi97/Low-shot-learning_-Deep-learning-project mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
schatty/matching-networks-tf mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
welkincici/MatchingNet mentioned on GitHubtfSyntology: not harvested report
wenbinlee/defensivefsl mentioned on GitHubpytorchSyntology: not harvested report
yijiuzai/Matching-Networks-for-One-Shot-Learning mentioned on GitHubtfMITSyntology: not harvested report
Lieberk/Paddle-MatchingNet paddleNOASSERTIONSyntology: not harvested report
Mind23-2/MindCode-5 mindsporeSyntology: not harvested report
ranpeng-git/few-shot-paddle paddleSyntology: not harvested 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

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

5ran · our draft was wrong
1ran; the contract check could not run
5ran
5unverified

Licence: 6 of the 16 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 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.

AntreasAntoniou/MatchingNetworks community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
augment_image in 12 papers data.py ran MIT (permissive) · 022f6566a93cb4b6 · report fixture: signature image:ndarray/3/float, k:int/0/int, channels:int/0/int · returned ndarray · level recorded 2026-09-26
build_experiment_folder utils/storage.py ran MIT (permissive) · c2ad5f5a2003fec1 · report fixture: signature experiment_name:str/0/str · returned tuple · level recorded 2026-09-26
load_statistics in 9 papers utils/storage.py ran MIT (permissive) · 348fc98221adb8ed · report fixture: signature log_path:str/0/str, log_name:str/0/str · returned dict · level recorded 2026-09-26
KamalM8/Few-Shot-learning-Fashion community (archive-listed) 1 sample, 0 ran · 1 unverified
lr_schedule in 30 papers experiments/proto_nets.py unverified MIT (permissive) · c7b885cfa7d6a165 · report
facebookresearch/low-shot-shrink-hallucinate community (archive-listed) 6 samples, 3 ran (3 instrument-failed) · 3 unverified
encode_lowshot_trainset matching_network.py ran; the contract check could not run (RAISES) licence not identified · pointer only · f48ebd2b61e5d2ee · report fixture: returned tuple · level recorded 2026-09-22
perelement_accuracy matching_network.py ran · our draft was wrong fingerprinted licence not identified · pointer only · e8592464cb90d8a9 · report fixture: signature scores:Tensor/2/float, label_ind:ndarray/1/int · returned tuple · level recorded 2026-09-22
perelement_accuracy low_shot.py ran · our draft was wrong fingerprinted licence not identified · pointer only · bf3de7601f74fa35 · report fixture: signature scores:Tensor/2/float, labels:Tensor/1/int · returned tuple · level recorded 2026-09-22
get_test_loader in 10 papers low_shot.py unverified licence not identified · pointer only · e18676657d36d810 · report
train_matching_network matching_network.py unverified licence not identified · pointer only · e6d5e6bdc3bf15c4 · report
training_loop low_shot.py unverified licence not identified · pointer only · 3bfa0f8b278ac054 · report
fujenchu/matchingNet community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
mean_confidence_interval in 16 papers utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fbec209cee9a4df8 · report fixture: signature data:list/1/float, confidence:float/0/float · returned tuple · level recorded 2026-09-22
randomCrop in 16 papers dataloader.py ran Apache-2.0 (permissive) · 40e189283ad47450 · report fixture: signature img:ndarray/3/int, centralCrop:bool/0/bool · returned ndarray · level recorded 2026-09-26
read_miniImageNet_pathonly utils.py ran Apache-2.0 (permissive) · 9a4547e2e8c3de87 · report fixture: signature TESTMODE:bool/0/bool, miniImageNetPath:str/0/str, imgPerCls:int/0/int · returned list · level recorded 2026-09-26
get_combination_miniImageNet_5way1shot_random_pathonly_episode_variableWays utils.py unverified Apache-2.0 (permissive) · 65ca7af4547afb9c · report
schatty/matching-networks-tf community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
preprocess_config in 5 papers scripts/train/run_train.py ran · our draft was wrong MIT (permissive) · 5d3cb59c1da5b053 · report fixture: signature c:dict/0/? · returned dict · level recorded 2026-09-22
preprocess_config in 5 papers scripts/eval/run_eval.py ran · our draft was wrong MIT (permissive) · 53241b134fbef5ed · report fixture: signature c:dict/0/? · returned dict · level recorded 2026-09-22

Tasks

Few-Shot Image ClassificationFew-Shot LearningLanguage ModelingLanguage ModellingMetric LearningOne-Shot Learning

Datasets

Introduced by this paper, per the archive.

mini-Imagenet

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Meta-Dataset Matching Networks Accuracy 56.247 #20 of 22 Archive leaderboard report
Few-Shot Image Classification Meta-Dataset Rank Matching Networks Mean Rank 10.5 #11 of 13 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) MatchingNet (Vinyals et al., 2016) Accuracy 45.59 #5 of 12 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Matching Nets (Cosine Matching Fn) Accuracy 46.6 #104 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Matching Nets (Cosine Matching Fn) Accuracy 60 #95 of 95 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Matching Nets Accuracy 93.8% #15 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Matching Nets Accuracy 98.1 #14 of 17 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Matching Nets Accuracy 98.5% #13 of 19 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Matching Nets Accuracy 98.9 #16 of 16 Archive leaderboard report
Few-Shot Image Classification Stanford Cars 5-way (1-shot) Matching Nets FCE++ Accuracy 34.80 #6 of 6 Archive leaderboard report
Few-Shot Image Classification Stanford Cars 5-way (5-shot) Matching Nets FCE++ Accuracy 44.70 #6 of 6 Archive leaderboard report
Few-Shot Image Classification Stanford Dogs 5-way (5-shot) Matching Nets FCE++ Accuracy 47.50 #6 of 6 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