Datasets › CIFAR-FS

CIFAR-FS (CIFAR100 few-shots)

Introduced by Luca Bertinetto et al. in Meta-learning with differentiable closed-form solvers21 May 2018 archive 2025-07-28

CIFAR100 few-shots (CIFAR-FS) is randomly sampled from CIFAR-100 (Krizhevsky & Hinton, 2009) by using the same criteria with which miniImageNet has been generated. The average inter-class similarity is sufficiently high to represent a challenge for the current state of the art. Moreover, the limited original resolution of 32×32 makes the task harder and at the same time allows fast prototyping.

Source: Bertinetto et al. Image source: Bertinetto et al.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Few-Shot Image Classification · CIFAR-FS 5-way (5-shot) (1 judged, 0 placed), Few-Shot Image Classification · CIFAR-FS 5-way (1-shot) (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).

First row (archive order)PaperCode
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) CAML [Laion-2b] Accuracy 93.5 Context-Aware Meta-Learning cfifty/CAML 39 Compare
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) PT+MAP+SF+SOT (transductive) Accuracy 89.94 The Self-Optimal-Transport Feature Transform danielshalam/bpa 38 Compare

Papers archive 2025-07-28

papers with a benchmark row: 32 · with a code link: 29 · where Syntology ran a sample: 12 (11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (12 of 32 with a benchmark row: 11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 32 of 32 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 206. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A 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” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Geometric Mean Improves Loss For Few-Shot Learning 0 2 24 Jan 2025 not harvested
The Balanced-Pairwise-Affinities Feature Transform 1 2 25 Jun 2024 not harvested
Context-Aware Meta-Learning 1 2 17 Oct 2023 official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification 0 2 18 Sep 2022 not harvested
Rethinking Generalization in Few-Shot Classification 1 2 15 Jun 2022 official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference 1 2 15 Apr 2022 official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified (4 pointer-only for licence)
The Self-Optimal-Transport Feature Transform 1 2 6 Apr 2022 not harvested
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning 1 2 17 Mar 2022 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
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients 3 8 24 Jan 2022 not harvested
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning 1 2 18 Oct 2021 not harvested
Sparse Spatial Transformers for Few-Shot Learning 1 2 27 Sep 2021 official (archive's flag): 3 ran · 3 ran (of which 0 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) · 3 unverified
Relational Embedding for Few-Shot Classification 1 2 22 Aug 2021 official (archive's flag): 11 ran · 11 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation 1 2 16 Jun 2021 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (1 pointer-only for licence)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning 1 2 1 Mar 2021 official (archive's flag): 1 ran · 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
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network 1 2 9 Feb 2021 not harvested
Sill-Net: Feature Augmentation with Separated Illumination Representation 1 2 6 Feb 2021 not harvested
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition 2 2 8 Jan 2021 official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (3 pointer-only for licence)
Constellation Nets for Few-Shot Learning 1 2 1 Jan 2021 not harvested
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks 2 2 13 Dec 2020 not harvested
Match Them Up: Visually Explainable Few-shot Image Classification 1 4 25 Nov 2020 not harvested
Region Comparison Network for Interpretable Few-shot Image Classification 1 4 8 Sep 2020 not harvested
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach 1 4 21 Jul 2020 not harvested
Self-supervised Knowledge Distillation for Few-shot Learning 2 2 17 Jun 2020 not harvested
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning 6 2 6 Jun 2020 official (archive's flag): 3 ran · 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 (12 pointer-only for licence)
Adaptive Subspaces for Few-Shot Learning 1 2 1 Jun 2020 not harvested
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients 2 2 27 Apr 2020 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (5 pointer-only for licence)
Instance Credibility Inference for Few-Shot Learning 1 2 26 Mar 2020 not harvested
Task Augmentation by Rotating for Meta-Learning 1 4 8 Feb 2020 not harvested
Generalized Adaptation for Few-Shot Learning 0 2 25 Nov 2019 not harvested
Charting the Right Manifold: Manifold Mixup for Few-shot Learning 8 2 28 Jul 2019 not harvested
Meta-Learning with Differentiable Convex Optimization 7 2 7 Apr 2019 not harvested
Learning to Compare: Relation Network for Few-Shot Learning 13 1 16 Nov 2017 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • CIFAR-FS 5-way (1-shot)
  • CIFAR-FS 5-way (5-shot)
  • CIFAR-FS

3 variant names, as the archive lists them.

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