HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Fine Grained Image Classification On Oxford

評価指標

Accuracy
FLOPS
PARAMS

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
IELT99.64%--Fine-Grained Visual Classification via Internal Ensemble Learning Transformer
BiT-L (ResNet)99.63%--Big Transfer (BiT): General Visual Representation Learning
µ2Net (ViT-L/16)99.61%--An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
Wide-ResNet-101 (Spinal FC)99.30%--SpinalNet: Deep Neural Network with Gradual Input
BiT-M (ResNet)99.30%--Big Transfer (BiT): General Visual Representation Learning
Grafit (RegNet-8GF)99.1%--Grafit: Learning fine-grained image representations with coarse labels
TResNet-L99.1%--TResNet: High Performance GPU-Dedicated Architecture
TNT-B99.0%-65.6MTransformer in Transformer
Assemble-ResNet98.9%--Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
DeiT-B98.8%-86MTraining data-efficient image transformers & distillation through attention
DenseNet-201(Spinal FC)98.36--A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification
NAT-M498.3400M4.2MNeural Architecture Transfer
DenseNet-20198.29--A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification
NAT-M398.1250M3.7MNeural Architecture Transfer
ResNet50 (A1)97.9%4.124MResNet strikes back: An improved training procedure in timm
ResMLP-2497.9%--ResMLP: Feedforward networks for image classification with data-efficient training
NAT-M297.9195M3.4MNeural Architecture Transfer
SR-GNN97.9%9.830.9SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
ResMLP-1297.4%--ResMLP: Feedforward networks for image classification with data-efficient training
FixInceptionResNet-V295.7%--Fixing the train-test resolution discrepancy
0 of 25 row(s) selected.