Papers › Prototypical Networks for Few-shot Learning

Prototypical Networks for Few-shot Learning

15 Mar 2017NeurIPS 2017 12arXiv:1703.05175archive 2025-07-28

Jake Snell, Kevin Swersky, Richard S. Zemel

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

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 64 code samples: 62 from 29 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 64: 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. Where Syntology's instrument failed: 12 where our contract draft was wrong; 9 where the contract check could not run; 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): 61 samples from 28 repositories, 47 ran (28 with no instrument failure; 19 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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. 1 of the 50 samples that ran has no recorded date.

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

jakesnell/prototypical-networks officialpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
COAOX/Cifar-Prototypical mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
DrMMZ/ProtoNet mentioned on GitHubtfSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report
HenryCWoo/LTLProject mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Hsankesara/DeepResearch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
KamalM8/Few-Shot-learning-Fashion mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
Michedev/Prototypical-Networks mentioned on GitHubpytorchSyntology: not harvested report
RongKaiWeskerMA/INSTA mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Sha-Lab/FEAT mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
WangTianduo/Prototypical-Networks mentioned on GitHubpytorchSyntology: not harvested report
ajfisch/few-shot-cp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
akshatgarg99/FewShotLearning mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
amazon-research/dse mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
andrewbo29/mtm-meta-learning-sa mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
ash3n/Latent-Similarity mentioned on GitHubtfSyntology: not harvested report
ash3n/Prototypical-Network-TF mentioned on GitHubtfSyntology: not harvested report
barnrang/Prototypical-network-keras-reimplementation mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
cnielly/prototypical-networks-omniglot mentioned on GitHubpytorchSyntology: not harvested report
cyvius96/prototypical-network-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
ebadrian/metadl mentioned on GitHubtfApache-2.0Syntology: 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
goldblum/AdversarialQuerying mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
joshfp/fellowship.ai mentioned on GitHubpytorchSyntology: not harvested report
joshfp/one-shot-learning mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
jsalbert/prototypical-networks mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
lif31up/prototypical-network mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
mariehane/prototypical-networks mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
maxstrobel/HCN-PrototypeLoss-PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
minseop-aitrics/FewshotLearning mentioned on GitHubtfSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
msfuxian/DualAttentionNet mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
oscarknagg/few-shot mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
schatty/prototypical-networks-tf mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ulises-jeremias/prototypical-networks-tf mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
yredwood/fewshot_blogpost mentioned on GitHubtfSyntology: 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); nothing checks that they implement this paper's method. report
zz990704/Reimplementation-Prototypical-network mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cnguyen10/few_shot_meta_learning pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PAC-Bayes meta-learning with implicit task-specific posteriors (arXiv:2003.02455; that paper's own run record: 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); nothing checks that they implement this paper's method. report
fabian57fabian/prototypical-networks-few-shot-learning pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hrdwsong/ProtoNet-Paddle paddleSyntology: not harvested report
learnables/learn2learn pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
sicara/easy-few-shot-learning pytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
skingorz/prototypeNet-paddle paddleSyntology: not harvested report
yangcedrus/ProtoNet paddleSyntology: not harvested 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

64 samples harvested: 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. “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 · honoured contract
12ran · our draft was wrong
9ran; the contract check could not run
24ran
14unverified

Licence: 19 of the 64 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 29 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. 2 samples are listed last, in a group without a repository. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

jakesnell/prototypical-networks official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Protonet protonets/models/few_shot.py ran · metamorphic tier: deterministic MIT (permissive) · a40352cfd6475ec3 · report fixture: returned Protonet · level recorded 2026-09-22
COAOX/Cifar-Prototypical community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ProtoNet src/protonet.py ran MIT (permissive) · 1bf49c188356596e · report fixture: returned ProtoNet · level recorded 2026-09-22
DrMMZ/ProtoNet community (archive-listed) 9 samples, 6 ran (3 instrument-failed) · 3 unverified
AccMetric model/ProtoNet.py ran · metamorphic tier: deterministic MIT (permissive) · 5885c112f3046823 · report fixture: returned AccMetric · level recorded 2026-09-22
CELoss model/ProtoNet.py ran MIT (permissive) · e3a0222fd8ed2d2f · report fixture: returned CELoss · level recorded 2026-09-22
GatherLayer in 12 papers model/ProtoNet.py ran · metamorphic tier: deterministic MIT (permissive) · 3144f593c6905e78 · report fixture: returned GatherLayer · level recorded 2026-09-22
backbone_protonet model/ProtoNet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f5c1a7acdfadd94b · report fixture: signature x:EagerTensor/4/float, filters:int/0/int, train_bn:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
conv_block in 95 papers model/ProtoNet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · bf404583e5ea3465 · report fixture: signature inputs:EagerTensor/4/float, filters:int/0/int, block:str/0/str, train_bn:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
identity_block in 32 papers model/ProtoNet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · f83f4ae2b6c3bc8d · report fixture: signature input_tensor:EagerTensor/4/float, filters:list/1/int, stage:int/0/int, block:str/0/str, train_bn:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
ProtoNet model/ProtoNet.py unverified MIT (permissive) · 4c32fdbf4bc74c91 · report
backbone_resnet model/ProtoNet.py unverified MIT (permissive) · d93d7b512badec9b · report
protonet model/ProtoNet.py unverified MIT (permissive) · 863c7b61e552662a · report
HenryCWoo/LTLProject community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ConvNet in 13 papers models/convnet_mini.py ran · metamorphic tier: deterministic MIT (permissive) · 0c8ab3061fc4f61b · report fixture: returned ConvNet · level recorded 2026-09-22
Hsankesara/DeepResearch community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Net in 54 papers Prototypical_Nets/prototypicalNet.py ran MIT (permissive) · fdc838c064947cc9 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
PrototypicalNet Prototypical_Nets/prototypicalNet.py unverified MIT (permissive) · dab17e19991f263e · report
KamalM8/Few-Shot-learning-Fashion community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
pairwise_distances in 34 papers
census: 14 implementations from 13 papers, 7 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
few_shot/proto.py ran · our draft was wrong MIT (permissive) · 9c31448b2eee894f · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, matching_fn:str/0/str, model:callable/0/? · returned Tensor · level recorded 2026-09-22
proto_net_episode few_shot/proto.py unverified MIT (permissive) · 0f5366e616c6d837 · report
RongKaiWeskerMA/INSTA community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ProtoNet model/models/protonet.py ran MIT (permissive) · c7a6d6154fec9ddf · report fixture: returned ProtoNet · level recorded 2026-09-22
FewShotModel_1 model/models/protonet.py unverified MIT (permissive) · e7053ecec6d213c4 · report
Sha-Lab/FEAT community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ProtoNet model/models/protonet.py ran · metamorphic tier: deterministic MIT (permissive) · 4eb979c22e4e42d0 · report fixture: returned ProtoNet · level recorded 2026-09-22
FewShotModel model/models/protonet.py unverified MIT (permissive) · 6137fa2b68c126ad · report
ajfisch/few-shot-cp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
R2D2Head chembl/modeling/encoders.py ran no licence file found · pointer only · 9c75d36a2cd52c03 · report fixture: signature query:Tensor/3/float, support:Tensor/3/float, support_targets:Tensor/2/float · returned Tensor · level recorded 2026-09-24
akshatgarg99/FewShotLearning community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
compute_prototypes in 7 papers Utils/protonet_calculations.py ran · our draft was wrong no licence file found · pointer only · 4de656fa284263c4 · report fixture: signature support:Tensor/2/float, k:int/0/int, n:int/0/int · returned Tensor · level recorded 2026-09-22
pairwise_distances in 34 papers
census: 14 implementations from 13 papers, 7 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
Utils/protonet_calculations.py ran · honoured contract fingerprinted no licence file found · pointer only · 276c42468f5e8af0 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22
proto_net_episode Utils/protonet_calculations.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · d76a7926a5b4328a · report fixture: signature model:callable/0/?, optimiser:SGD/0/?, loss_fn:callable/0/?, x:Tensor/2/float, y:Tensor/1/int, n_shot:int/0/int, k_way:int/0/int, q_queries:int/0/int, train:bool/0/bool · returned tuple · level recorded 2026-09-22
amazon-research/dse community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PSCBert pretrain/models/Transformers.py ran Apache-2.0 (permissive) · c9d933d5fb7c5095 · report fixture: returned PSCBert · level recorded 2026-09-22
andrewbo29/mtm-meta-learning-sa community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
ProtoNetHead protonet/models/classification_heads.py ran; the contract check could not run (RAISES) MIT (permissive) · 75cb52150d9a660a · report fixture: signature query:Tensor/3/float, support:Tensor/3/float, support_labels:Tensor/2/int, n_way:int/0/int, n_shot:int/0/int, device:device/0/?, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-22
computeGramMatrix in 8 papers protonet/models/classification_heads.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6134727f9d286287 · report fixture: signature A:Tensor/3/float, B:Tensor/3/float · returned Tensor · level recorded 2026-09-22
barnrang/Prototypical-network-keras-reimplementation community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
proto_dist util/loss.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 6ef2681ed9527bea · report fixture: signature x:tuple/1/EagerTensor · returned EagerTensor · level recorded 2026-09-22
cyvius96/prototypical-network-pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
Convnet convnet.py ran · metamorphic tier: deterministic MIT (permissive) · 03ab81be46e41dfb · report fixture: returned Convnet · level recorded 2026-09-22
conv_block in 95 papers convnet.py ran · our draft was wrong MIT (permissive) · b0a1286b15398404 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22
goldblum/AdversarialQuerying community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
ProtoNetHead models/classification_heads.py ran · our draft was wrong MIT (permissive) · 58af5957818ea856 · report fixture: returned Tensor · level recorded 2026-09-22
joshfp/one-shot-learning community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
EmbeddingFunction model.py ran no licence file found · pointer only · fe0021aa329ae860 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
conv_block in 95 papers model.py ran · our draft was wrong no licence file found · pointer only · 57d2c3e6cce78748 · report fixture: signature in_n:int/0/int, filters_n:int/0/int · returned Sequential · level recorded 2026-09-22
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0d9f00b53a9558f8 · report fixture: signature t1:Tensor/2/float, t2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
PrototypicalNetwork model.py unverified no licence file found · pointer only · 9bd97fbc6d63a34b · report
jsalbert/prototypical-networks community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
conv_block in 95 papers models/convnet_mini.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9d556d61294bb0a8 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input
utils.py ran fingerprinted MIT (permissive) · e439ae68f44dd2f2 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-26
accuracy_top_k utils.py unverified MIT (permissive) · f006ac7d22562283 · report
compute_accuracy in 81 papers utils.py unverified MIT (permissive) · d91ab830cd1fc8e4 · report
lif31up/prototypical-network community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ProtoNet model/ProtoNet.py ran MIT (permissive) · 516db6627dd0d56e · report fixture: signature x:Tensor/4/float, prototypes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Config in 46 papers model/ProtoNet.py unverified MIT (permissive) · be2b72d9c5987b86 · report
mariehane/prototypical-networks community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrototypicalNetwork prototypical.py ran no licence file found · pointer only · f5933c3730b6f339 · report fixture: signature support:Tensor/3/float, queries:Tensor/3/float · returned Tensor · level recorded 2026-09-24
maxstrobel/HCN-PrototypeLoss-PyTorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
PrototypeLoss processor/processor_protonet.py ran · metamorphic tier: deterministic MIT (permissive) · 17f40aa50a000486 · report fixture: signature z_query:Tensor/2/float, z_support:Tensor/2/float, n_class:int/0/int, n_support:int/0/int, n_query:int/0/int · returned tuple · level recorded 2026-09-22
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
processor/processor_protonet.py ran · our draft was wrong fingerprinted MIT (permissive) · 7ad5cda37c731a0a · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22
minseop-aitrics/FewshotLearning community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
tf_acc ProtoNet/lib/networks.py ran · honoured contract no licence file found · pointer only · d76ff0bd573853cd · report fixture: signature p:EagerTensor/2/float, y:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
Network in 40 papers ProtoNet/lib/networks.py unverified no licence file found · pointer only · 7031de287b846201 · report
ProtoNet ProtoNet/lib/networks.py unverified no licence file found · pointer only · ff981c1b19834fdd · report
orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ProtoNet src/protonet.py ran · metamorphic tier: deterministic MIT (permissive) · 0b1720468e69b9da · report fixture: returned ProtoNet · level recorded 2026-09-22
oscarknagg/few-shot community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
compute_prototypes in 7 papers few_shot/proto.py ran · our draft was wrong MIT (permissive) · c442feb515d4d8f3 · report fixture: signature support:Tensor/2/float, k:int/0/int, n:int/0/int · returned Tensor · level recorded 2026-09-22
pairwise_distances in 34 papers
census: 14 implementations from 13 papers, 7 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
few_shot/proto.py ran; the contract check could not run (RAISES) MIT (permissive) · 264452c073b536a8 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, matching_fn:str/0/str · returned Tensor · level recorded 2026-09-22
proto_net_episode few_shot/proto.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 228cdfe23ddb6e6a · report fixture: signature model:callable/0/?, optimiser:SGD/0/?, loss_fn:callable/0/?, x:Tensor/2/float, y:Tensor/1/int, n_shot:int/0/int, k_way:int/0/int, q_queries:int/0/int, distance:str/0/str, train:bool/0/bool · returned tuple · level recorded 2026-09-22
schatty/prototypical-networks-tf community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Prototypical prototf/models/prototypical.py ran MIT (permissive) · 180e010d21e18799 · report fixture: returned Prototypical · level recorded 2026-09-22
ulises-jeremias/prototypical-networks-tf community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Prototypical protonet/models/prototypical.py ran MIT (permissive) · 08f5684e7687d43e · report fixture: returned Prototypical · level recorded 2026-09-22
calc_euclidian_dists protonet/models/prototypical.py ran · honoured contract fingerprinted MIT (permissive) · a84bbc21fe9abc8d · report fixture: signature x:EagerTensor/2/float, y:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
zz990704/Reimplementation-Prototypical-network community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
few_shot_euclidean_similarity protonet.py ran · honoured contract fingerprinted no licence file found · pointer only · 24477e2d27f5e8f7 · report fixture: signature query:Tensor/2/float, prototypes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
fabian57fabian/prototypical-networks-few-shot-learning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrototypicalNetwork src/prototypical_net.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · aa420da10668ccd5 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
learnables/learn2learn community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PrototypicalClassifier learn2learn/nn/protonet.py ran fingerprinted MIT (permissive) · 46fbc98d3054326d · report fixture: returned PrototypicalClassifier · level recorded 2026-09-22
compute_prototypes in 7 papers learn2learn/nn/protonet.py ran · honoured contract fingerprinted MIT (permissive) · b737a25e6c29ebc7 · report fixture: signature support:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
sicara/easy-few-shot-learning community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
FewShotClassifier easyfsl/methods/prototypical_networks.py ran MIT (permissive) · f798e1a78274cb31 · report fixture: signature images:Tensor/2/float · returned Tensor · level recorded 2026-09-24
PrototypicalNetworks easyfsl/methods/prototypical_networks.py ran MIT (permissive) · 341b0d9276c53ee2 · report fixture: signature images:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_prototypes in 7 papers easyfsl/methods/prototypical_networks.py ran · our draft was wrong fingerprinted MIT (permissive) · 9b846f6eab1ad481 · report fixture: signature support_features:Tensor/2/float, support_labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv_block in 95 papers repository not located ran · our draft was wrong licence of this copy not recorded · 4018d80d0425da98 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded, date not recorded
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 4dd319c45d372246 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22

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.

27 assemblies on this paper: 27 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

27 sibling assemblies for Prototypical Networks (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 27 sibling assemblies; the other 15 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. Convnet entry · level 1 · ran · 03ab81be46e41dfb
  2. conv_block helper · level 1 · ran · our draft was wrong · b0a1286b15398404

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 27 siblings

  1. ProtoNet entry · level 1 · ran · 4eb979c22e4e42d0
  2. FewShotModel helper · level 0 · unverified · 6137fa2b68c126ad

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 9 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. ProtoNet entry · level 0 · unverified · 4c32fdbf4bc74c91
  2. protonet model · level 0 · unverified · 863c7b61e552662a
  3. AccMetric metric · level 1 · ran · 5885c112f3046823
  4. CELoss loss · level 1 · ran · e3a0222fd8ed2d2f
  5. GatherLayer helper · level 1 · ran · 3144f593c6905e78
  6. backbone_protonet model · level 1 · ran; the contract check could not run (RAISES) · f5c1a7acdfadd94b
  7. backbone_resnet helper · level 0 · unverified · d93d7b512badec9b
  8. conv_block model · level 1 · ran; the contract check could not run (RAISES) · bf404583e5ea3465
  9. identity_block helper · level 1 · ran; the contract check could not run (RAISES) · f83f4ae2b6c3bc8d

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. Protonet entry · level 1 · ran · a40352cfd6475ec3
  2. euclidean_dist metric · level 1 · ran · our draft was wrong · 4dd319c45d372246

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. ConvNet entry · level 1 · ran · 0c8ab3061fc4f61b
  2. conv_block model · level 1 · ran · our draft was wrong · 9d556d61294bb0a8

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 4 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. ProtoNet entry · level 0 · unverified · ff981c1b19834fdd
  2. Network helper · level 0 · unverified · 7031de287b846201
  3. cross_entropy loss · level 0 · unverified · f4fb81c626a087a4
  4. tf_acc metric · level 1 · ran · honoured contract · d76ff0bd573853cd

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. proto_net_episode entry · level 1 · ran; the contract check could not run (RAISES) · d76a7926a5b4328a
  2. compute_prototypes model · level 1 · ran · our draft was wrong · 4de656fa284263c4
  3. pairwise_distances metric · level 1 · ran · honoured contract · 276c42468f5e8af0

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; 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) · 1 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. PrototypicalNet entry · level 0 · unverified · dab17e19991f263e
  2. Net model · level 1 · ran · fdc838c064947cc9

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 27 siblings

  1. PrototypicalClassifier entry · level 1 · ran · 46fbc98d3054326d
  2. compute_prototypes helper · level 1 · ran · honoured contract · b737a25e6c29ebc7

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. few_shot_euclidean_similarity entry · level 1 · ran · honoured contract · 24477e2d27f5e8f7

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. ProtoNetHead entry · level 1 · ran; the contract check could not run (RAISES) · 75cb52150d9a660a
  2. computeGramMatrix helper · level 1 · ran; the contract check could not run (RAISES) · 6134727f9d286287

harvested Assembly for Prototypical Networks (graph method: Prototypical Networks). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 27 siblings

  1. ProtoNet entry · level 1 · ran · 0b1720468e69b9da
  2. conv_block model · level 1 · ran · our draft was wrong · 4018d80d0425da98
  1. ProtoNet · 512eaae8dfbda4c3 · 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. ProtoNet · 5ef246980600c6c8 · 2 bricks; individually on a fixture: 1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. proto_net_episode · 6783f83b8e90f6fe · 3 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. proto_net_episode · 6ece29c8c6a0b3c4 · 4 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. ProtoNetHead · 7758847b23b6884c · 3 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. Prototypical · 8856987c1c486c9d · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 · assemblies[17] in the JSON twin
  7. PSCBert · 88cd5c059e73c9cb · 1 brick; individually on a fixture: 1 ran (of which 1 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 one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. PrototypicalNetwork · 9dafbbb7637f68bd · 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 · assemblies[19] in the JSON twin
  9. ProtoNet · a31289db16be0dcd · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. proto_dist · b0775274c1d172a0 · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. Prototypical · b1a68c923f779cec · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 · assemblies[22] in the JSON twin
  12. PrototypicalNetwork · c08710e265f359ca · 4 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. PrototypicalNetworks · c75b435ea4d305ef · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. PrototypicalNetwork · cac599371004c414 · 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 · assemblies[25] in the JSON twin
  15. PrototypeLoss · ee9f2234153cdddf · 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin

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="1703.05175") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Category-Agnostic Pose EstimationFew-Shot Image ClassificationFew-Shot LearningGeneral ClassificationInductive BiasMeta-LearningOne-Shot LearningZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Category-Agnostic Pose Estimation MP100 ProtoNet Mean PCK@0.2 - 1shot 44.78 #5 of 5 Archive leaderboard report
Few-Shot Image Classification CUB 200 50-way (0-shot) Prototypical Networks Accuracy 54.6 #1 of 4 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 1-shot) ProtoNet 1:1 Accuracy 53.6 #10 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 5-shot) ProtoNet 1:1 Accuracy 74.2 #8 of 12 Archive leaderboard report
Few-Shot Image Classification Meta-Dataset Prototypical Networks Accuracy 60.573 #17 of 22 Archive leaderboard report
Few-Shot Image Classification Meta-Dataset Rank Prototypical Networks Mean Rank 8.5 #8 of 13 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) ProtoNet (Snell et al., 2017) Accuracy 45.31 #6 of 12 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Prototypical Networks (Higher Way) Accuracy 34.6 #9 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Prototypical Networks Accuracy 32.9 #10 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Prototypical Networks (Higher Way) Accuracy 50.1 #8 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Prototypical Networks Accuracy 49.3 #9 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Prototypical Networks Accuracy 49.42 #101 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (10-shot) Prototypical Networks Accuracy 74.3 #5 of 5 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Prototypical Networks Accuracy 68.20 #86 of 95 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Prototypical Networks Accuracy 96% #12 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Prototypical Networks Accuracy 98.8 #9 of 17 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Prototypical Networks Accuracy 98.9% #10 of 19 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Prototypical Networks Accuracy 99.7 #9 of 16 Archive leaderboard report
Few-Shot Image Classification Stanford Cars 5-way (1-shot) Prototypical Nets++ Accuracy 40.90 #5 of 6 Archive leaderboard report
Few-Shot Image Classification Stanford Cars 5-way (5-shot) Prototypical Nets++ Accuracy 52.93 #5 of 6 Archive leaderboard report
Few-Shot Image Classification Stanford Dogs 5-way (5-shot) Prototypical Nets++ Accuracy 48.19 #5 of 6 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Prototypical Networks (Higher Way) Accuracy 38.6 #7 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Prototypical Networks Accuracy 37.3 #8 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Prototypical Networks (Higher Way) Accuracy 58.3 #6 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Prototypical Networks Accuracy 57.8 #9 of 13 Archive leaderboard report
Image Classification Tiered ImageNet 5-way (5-shot) Prototypical Net Accuracy 69.57 #6 of 7 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