AI Paper Atlas

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

miniImageNet 5-way 5-shot leaderboard

191 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on miniImageNet 5-way 5-shot. Best accuracy: 99.07 (MPA, 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 5-shot · accuracy

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

#accuracy ↑MethodPaperTopic
199.07MPA
CLIP ViT-L/14
MPA: Multimodal Prototype Augmentation for Few-Shot Learning
AAAI 2026 · Table 3
Zero-/few-shot and meta-learning
299.05EfficientFSL
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
399.04Ours (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
498.3SPM
ViT-small
Self-Prompt Mechanism for Few-Shot Image Recognition
AAAI 2024 · Table 1
Zero-/few-shot and meta-learning
597.41F2SST
ViT-S/16
F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification
AAAI 2026 · Table 1
Zero-/few-shot and meta-learning
696.12LoRA 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
796.06VPG (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
893.21NAO-centroid
ResNet-12
Norm-guided latent space exploration for text-to-image generation
NeurIPS 2023 · Few-shot results table
Text-to-image diffusion
992.69CML-BGNN
Conv4
Learning from the Past: Continual Meta-Learning with Bayesian Graph Neural Networks
AAAI 2020 · Table 1
Online and replay-based
1092.14CAMeLU
ResNet-50 (ImageNet-964)
Unsupervised Meta-Learning via In-Context Learning
ICLR 2025 · Table: Comparative results
Zero-/few-shot and meta-learning
181 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.