</> Code with Papers by Syntology

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.

HomepageBenchmarksPapers JSON

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.

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

30 shown of 32 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 206. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples 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 ran 5 of 16 samples (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 ran 2 of 3 samples (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 ran 6 of 19 samples (13 unverified)
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 ran 4 of 5 samples (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 ran 0 of 6 samples (6 unverified)
Relational Embedding for Few-Shot Classification 1 2 22 Aug 2021 ran 11 of 13 samples (2 unverified)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation 1 2 16 Jun 2021 ran 1 of 10 samples (9 unverified)
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning 1 2 1 Mar 2021 ran 1 of 1 samples (0 unverified)
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 ran 3 of 3 samples (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 ran 10 of 26 samples (16 unverified; 11 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 ran 3 of 5 samples (2 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

The full list of 32 is in the JSON twin.

Dataset loaders archive 2025-07-28

learn2learn.netlearnables/learn2learnpytorch
bertinetto/r2d2pytorch

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

Tasks archive 2025-07-28

Few-Shot Image Classification

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

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