Browse State-of-the-Art › Few-Shot Learning

Few-Shot Learning

1,297 papers with code · 27 benchmarks · 45 datasets archive 2025-07-28

AudioComputer VisionMethodologyNatural Language Processing

Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.

Source: Penalty Method for Inversion-Free Deep Bilevel Optimization

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

27 leaderboard tables shown for this task, 27 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 27 until expanded.

Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): DTD (1 judged, 0 placed), SST-2 Binary classification (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MedConceptsQA (12 rows) gpt-4-0125-preview GPT-4 Technical Report code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
DTD (4 rows) SaSPA + CAL Advancing Fine-Grained Classification by Structure and Subject... code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
FGVC Aircraft (4 rows) SaSPA + CAL Advancing Fine-Grained Classification by Structure and Subject... code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
Mini-ImageNet - 5-Shot Learning (3 rows) BGNN — — — Compare
Mini-Imagenet 5-way (1-shot) (3 rows) EASY (transductive) EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art... code — Compare
Stanford Cars (3 rows) SaSPA + CAL Advancing Fine-Grained Classification by Structure and Subject... code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
Mini-ImageNet - 1-Shot Learning (2 rows) HCTransformers Attribute Surrogates Learning and Spectral Tokens Pooling in... code Syntology official (archive's flag): 4 ran · 4 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; 2 where Syntology's instrument failed) · 1 unverified Compare
PubMedQA (2 rows) MetaGen Blended RAG (zero-shot) MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A... code — Compare
Caltech101 (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
CaseHOLD (1 row) CoT-T5-11B (1024 Shot) The CoT Collection: Improving Zero-shot and Few-shot Learning of... code — Compare
CR (1 row) DART Differentiable Prompt Makes Pre-trained Language Models Better... code Syntology official (archive's flag): 2 ran · 3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
EuroSAT (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
Flowers-102 (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
food101 (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
GLUE QQP (1 row) DART Differentiable Prompt Makes Pre-trained Language Models Better... code Syntology official (archive's flag): 2 ran · 3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
Large COVID-19 CT scan slice dataset (1 row) CovidExpert CovidExpert: A Triplet Siamese Neural Network framework for the... — — Compare
MedNLI (1 row) CoT-T5-11B (1024 Shot) The CoT Collection: Improving Zero-shot and Few-shot Learning of... code — Compare
Mini-ImageNet - 10-Shot Learning (1 row) UNEM-Gaussian UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning code — Compare
Mini-ImageNet - 20-Shot Learning (1 row) UNEM-Gaussian UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning code — Compare
MR (1 row) DART Differentiable Prompt Makes Pre-trained Language Models Better... code Syntology official (archive's flag): 2 ran · 3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
MRPC (1 row) DART Differentiable Prompt Makes Pre-trained Language Models Better... code Syntology official (archive's flag): 2 ran · 3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
OxfordPets (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
SST-2 Binary classification (1 row) DART Differentiable Prompt Makes Pre-trained Language Models Better... code Syntology official (archive's flag): 2 ran · 3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
StanforCars (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
SUN397 (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare
tieredImageNet - 5-shot (1 row) UNEM-Gaussian UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning code — Compare
UCF101 (1 row) Variational Prompt Tuning Bayesian Prompt Learning for Image-Language Model Generalization code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 2 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

45 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 45 until expanded.

Subtasks archive 2025-07-28

12 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 2,964 · with a code link: 1,297 · where Syntology ran a sample: 373 (305 with a run with no instrument failure, 68 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (373 of 2,964 tagged: 305 with a run with no instrument failure, 68 where every run was a failure of Syntology's instrument)

Page 1 of 30: papers 1 to 100 of 2,964, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 65 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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