AI Paper Atlas

Research map / Benchmarks / miniImageNet 5-way 1-shot

miniImageNet 5-way 1-shot leaderboard

193 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on miniImageNet 5-way 1-shot. Best accuracy: 98.34 (EfficientFSL, 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.

miniImageNet 5-way 1-shot · accuracy

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

#accuracy ↑MethodPaperTopic
198.34EfficientFSL
ViT-B/16 (ImageNet-21K)
EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning In Vision Transformers
AAAI 2026 · Table 1
Pruning and efficient tuning
294.68Ours
DINO ViT-S
Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning
ICCV 2025 · Tables 5-7
Domain adaptation and generalization
389.27F2SST
ViT-S/16
F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification
AAAI 2026 · Table 1
Zero-/few-shot and meta-learning
488.62CML-BGNN
Conv4
Learning from the Past: Continual Meta-Learning with Bayesian Graph Neural Networks
AAAI 2020 · Table 1
Online and replay-based
588.6LoRA 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
685.76VPG (training-free)
DINO ViT-S/16
Variational Patch Gating for Training-Free Few-Shot Classification
ECCV 2026 · Table 3
Zero-/few-shot and meta-learning
782.66PTN
WRN-28-10
PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning
AAAI 2021 · Table: comparison with state-o
Semi-supervised learning
882.16SemDGGN
Swin-T
Dual-Geometry Graph Network: Unifying Local and Global Priors for Few-Shot Learning
AAAI 2026 · Table 1
Graph self-supervised learning
981.14ECER-FSL
Visformer-T
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
AAAI 2025 · Table 1
CLIP and zero-shot
1080.64Ours
WRN28-10 (transductive)
Transductive Few-Shot Classification on the Oblique Manifold
ICCV 2021 · Table 1
Zero-/few-shot and meta-learning
183 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.