AI Paper Atlas

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

CUB 5-way 5-shot leaderboard

43 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CUB 5-way 5-shot. Best accuracy: 97.92 (NAO-centroid, NeurIPS 2023).

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 5-shot · accuracy

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

#accuracy ↑MethodPaperTopic
197.92NAO-centroid
ResNet-12
Norm-guided latent space exploration for text-to-image generation
NeurIPS 2023 · Few-shot results table
Text-to-image diffusion
297.67LoRA 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
395.57VPG (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
495.44FeatWalk
DeepBDC, ResNet-18
FeatWalk: Enhancing Few-Shot Classification through Local View Leveraging
AAAI 2024 · Table 2
Zero-/few-shot and meta-learning
594.97Ours
ResNet-18 (transductive)
Transductive Few-Shot Classification on the Oblique Manifold
ICCV 2021 · Table 2
Zero-/few-shot and meta-learning
694.73Bi-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
793.09MetaIRNet
ResNet18, ImageNet
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
NeurIPS 2019 · Appendix, Five-shot Experiment
Zero-/few-shot and meta-learning
892.97RENet-ventral
RENet
Exploring Tuning Characteristics of Ventral Stream’s Neurons for Few-Shot Image Classification
AAAI 2023 · Table 2
Open-set and few-shot detection
992.54CPN
ResNet12
Compositional Prototypical Networks for Few-Shot Classification
AAAI 2023 · Table 1
Zero-/few-shot and meta-learning
1092.45TransVLAD
ViT-B (MAE)
TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning
ECCV 2022 · Table 2
Zero-/few-shot and meta-learning
33 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.