AI Paper Atlas

Research map / Benchmarks / CIFAR-FS 5-way 5-shot

CIFAR-FS 5-way 5-shot leaderboard

63 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-FS 5-way 5-shot. Best accuracy: 97.71 (F2SST, AAAI 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-way 5-shot · accuracy

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

#accuracy ↑MethodPaperTopic
197.71F2SST
ViT-S/16
F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification
AAAI 2026 · Table 2
Zero-/few-shot and meta-learning
297.64MPA
CLIP ViT-L/14
MPA: Multimodal Prototype Augmentation for Few-Shot Learning
AAAI 2026 · Table 3
Zero-/few-shot and meta-learning
397.05LoRA Recycle
ViT-B/16 CLIP
LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
CVPR 2025 · Table 2
Instruction and fine-tuning
494.85NAO-centroid
ResNet-12
Norm-guided latent space exploration for text-to-image generation
NeurIPS 2023 · Few-shot results table
Text-to-image diffusion
594.6EfficientFSL
ViT-S/16 (ImageNet-1K)
EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning In Vision Transformers
AAAI 2026 · Table 1
Pruning and efficient tuning
694.13CAD
ResNet12
CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification
CVPR 2022 · Table 2
Zero-/few-shot and meta-learning
793.62Ours (IN1K, Sup., Swin-S)
Swin-S
Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention
AAAI 2024 · Table 1
Zero-/few-shot and meta-learning
893.1SPM
ViT-small
Self-Prompt Mechanism for Few-Shot Image Recognition
AAAI 2024 · Table 2
Zero-/few-shot and meta-learning
992.27DGGN
ResNet-12
Dual-Geometry Graph Network: Unifying Local and Global Priors for Few-Shot Learning
AAAI 2026 · Table 1
Graph self-supervised learning
1091ECKPN
ResNet-12
ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-Shot Learning
CVPR 2021 · Table: Few-shot classification
Zero-/few-shot and meta-learning
53 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.