AI Paper Atlas

Research map / Benchmarks / miniImageNet 1-shot

miniImageNet 1-shot leaderboard

39 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on miniImageNet 1-shot. Best accuracy: 84.78 (MetaFormer-A, ICML 2024).

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 1-shot · accuracy

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

#accuracy ↑MethodPaperTopic
184.78MetaFormer-A
ViT-Small
One Meta-tuned Transformer is What You Need for Few-shot Learning
ICML 2024 · Table 1
Attention and transformers
284.35protoLP*
ResNet-12
Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement
CVPR 2023 · Table 1
Zero-/few-shot and meta-learning
383.66VT-FSL
Visformer-T
VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
NeurIPS 2025 · Table 1
CLIP and zero-shot
482.16Simple CNAPS
ResNet18
Improved Few-Shot Visual Classification
CVPR 2020 · Table: mini/tieredImageNet
Zero-/few-shot and meta-learning
581.69DVLA-RLDVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
ICLR 2026 · Table 1
CLIP and zero-shot
674.85COIN
WRN-28-10
Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networks
TPAMI 2025 · Table 2
Fast diffusion sampling
774.84ProtoNet + R-SVAE
ProtoNet; ResNet-12
Generating Representative Samples for Few-Shot Classification
CVPR 2022 · Table 1
Zero-/few-shot and meta-learning
874.02noHub-S + SIAMESE
ResNet-18
Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings
CVPR 2023 · Appendix results table
Zero-/few-shot and meta-learning
973.81DPViT
ViT-S
Mitigating the Effect of Incidental Correlations on Part-based Learning
NeurIPS 2023 · Table 1
Recognition and long-tail
1073.6IFSL + Ours
WRN-28-10
argmax centroid
NeurIPS 2021 · Table 1
Domain adaptation and generalization
29 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.