AI Paper Atlas

Research map / Benchmarks / Flowers102

Flowers102 leaderboard

51 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Flowers102. Best accuracy: 99.7 (TURTLE, 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.

Flowers102 · accuracy

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

#accuracy ↑MethodPaperTopic
199.7TURTLE
CLIP RN50 + DINOv2 ViT-g/14
Let Go of Your Labels with Unsupervised Transfer
ICML 2024 · Table
Zero-/few-shot and meta-learning
299.5LOFF-TA
DINOv2 ViT-B
Learning from Offline Foundation Features with Tensor Augmentations
NeurIPS 2024 · Expanded results table
RNNs and normalization
399.3Ours (full)
CLIP ViT-B/16
Provably Improving Generalization of Few-shot models with Synthetic Data
ICML 2025 · Main results table
Zero-/few-shot and meta-learning
499.28SVFT Banded d=2
ViT-B
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
NeurIPS 2024 · Table: Image Classification
Pruning and efficient tuning
599.25FedPHA
CLIP ViT-B16
FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
ICML 2025 · Table 1
Personalized and heterogeneous FL
698.9SVT-H-BScattering Vision Transformer: Spectral Mixing Matters
NeurIPS 2023 · Transfer learning results tabl
CNN features
798.84SurPL
CLIP ViT-B/16
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models
ICML 2025 · Table 4
CLIP and zero-shot
898.8FractalDB-10k
DeiT-Ti/16
Can Vision Transformers Learn without Natural Images?
AAAI 2022 · Comparison table
Attention and transformers
998.55AdaBet
ViT (ImageNet pretrained)
AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
CVPR 2026 · Table 2
RNNs and normalization
1097.85TransBoost (transductive)
ResNet50
TransBoost: Improving the Best ImageNet Performance using Deep Transduction
NeurIPS 2022 · Appendix Table
Pruning and efficient tuning
41 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.