AI Paper Atlas

Research map / Benchmarks / CIFAR-FS 5-shot

CIFAR-FS 5-shot leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-FS 5-shot. Best accuracy: 94.55 (TAIL, ICML 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-FS 5-shot · accuracy

13 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
194.55TAIL
ViT-H
Universal Algorithm-Implicit Learning
ICML 2026 · Table 2
Zero-/few-shot and meta-learning
292.21MetaFormer-A
ViT-Small
One Meta-tuned Transformer is What You Need for Few-shot Learning
ICML 2024 · Table 2
Attention and transformers
391.52protoLP*
ResNet-12
Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement
CVPR 2023 · CIFAR-FS results table
Zero-/few-shot and meta-learning
491.45VT-FSL
Visformer-T
VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
NeurIPS 2025 · Table 2
CLIP and zero-shot
590.59DVLA-RLDVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
ICLR 2026 · Table 1
CLIP and zero-shot
689.54MCT + Meta-MaxUp
MCT, ResNet-12
Data Augmentation for Meta-Learning
ICML 2021 · Table: Few-shot classification
Zero-/few-shot and meta-learning
788.45PSST
WRN-28-10
Pareto Self-Supervised Training for Few-Shot Learning
CVPR 2021 · CIFAR-FS state-of-the-art comp
Self-supervised and contrastive
887.24HFA (Ours)
ResNet18
Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds
NeurIPS 2022 · Table 1
Recognition and long-tail
986.71SEMAN-G
ResNet12
Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition
CVPR 2022 · CIFAR-FS results table
Zero-/few-shot and meta-learning
1086.3Classical w/ R_FC
MetaOptNet
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
ICML 2020 · Table: feature clustering resu
Zero-/few-shot and meta-learning
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.