AI Paper Atlas

Research map / Benchmarks / Flowers

Flowers leaderboard

40 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Flowers. Best accuracy: 99.6 (ExFractalDB-1k*, CVPR 2022).

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.

Flowers · accuracy

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

#accuracy ↑MethodPaperTopic
199.6ExFractalDB-1k*Replacing Labeled Real-Image Datasets With Auto-Generated Contours
CVPR 2022 · Table 9
Self-supervised and contrastive
299.1TAPS
ViT-S/16
Task Adaptive Parameter Sharing for Multi-Task Learning
CVPR 2022 · Table: accuracy across archite
Pruning and efficient tuning
399.06Hint-Aug + LoRA
ImageNet-pretrained ViT-Base
Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning
CVPR 2023 · Supplementary Table 2
Pruning and efficient tuning
498.93BiSAM (-log)
ViT-B/16
Improving SAM Requires Rethinking its Optimization Formulation
ICML 2024 · Image fine-tuning table
Prediction and decision losses
598.9VisualAtom-1k
ViT-T
Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves
CVPR 2023 · Table: comparison of pre-train
Pruning and efficient tuning
698.8DearKD-B
DeiT-B
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
CVPR 2022 · Table 5
Attention and transformers
798.8EfficientNetV2-LEfficientNetV2: Smaller Models and Faster Training
ICML 2021 · Table: Transfer Learning Perfo
Neural architecture search
898.8EfficientNet-B7
EfficientNet-B0
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
ICML 2019 · Table: EfficientNet Performanc
CNN design
998.7CMT-SCMT: Convolutional Neural Networks Meet Vision Transformers
CVPR 2022 · Table: Transfer Learning Resul
CNN design
1098.6MoE Jetpack (ConvNeXt-F)
ConvNeXt-T, ImageNet-21k
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
NeurIPS 2024 · Table: Performance comparison
Mixture of experts
30 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.