AI Paper Atlas

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

CUB 5-way 1-shot leaderboard

37 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CUB 5-way 1-shot. Best accuracy: 96.4 (Ours, AAAI 2025).

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.

CUB 5-way 1-shot · accuracy

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

#accuracy ↑MethodPaperTopic
196.4Ours
Qwen-VL-Chat-Int4
Making Large Vision Language Models to Be Good Few-Shot Learners
AAAI 2025 · Table: comparison on general d
CLIP and zero-shot
291.12LoRA 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
387.29CPN
ResNet12
Compositional Prototypical Networks for Few-Shot Classification
AAAI 2023 · Table 1
Zero-/few-shot and meta-learning
486.02VPG (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
585.87Ours
ResNet-18 (transductive)
Transductive Few-Shot Classification on the Oblique Manifold
ICCV 2021 · Table 2
Zero-/few-shot and meta-learning
685.67FeatWalk
DeepBDC, ResNet-18
FeatWalk: Enhancing Few-Shot Classification through Local View Leveraging
AAAI 2024 · Table 2
Zero-/few-shot and meta-learning
785.44Bi-FRN
ResNet-12
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
AAAI 2023 · Table 1
Zero-/few-shot and meta-learning
884.8MetaIRNet (+FinetuneGAN, Flip)
ResNet18 (ImageNet)
Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition
TPAMI 2022 · Table 2
Zero-/few-shot and meta-learning
984.8MetaIRNet + FinetuneGAN, Flip
ResNet18, ImageNet
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
NeurIPS 2019 · Table 1
Zero-/few-shot and meta-learning
1084.2ADV-CE
WRN
Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization
NeurIPS 2022 · Table 1
Zero-/few-shot and meta-learning
27 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.