List your company
ResearchFormerly WizWand

Image Classification on ImageNet (1%)

81.6Top-1 AccuracyREACT
21.07236.78652.568.214Nov 29, 2023
Updated 8mo ago

Evaluation results

MethodLinks
REACTBackbone=ViT-L, Protocol=REACT2023.1181.6
Meta Co-TrainingBackbone=MLP, Trained on large model embeddings=true, Protocol=Meta Co-Training2023.1180.7
CLIPBackbone=ViT-L, Protocol=Fine-tuned2023.1180.5
Co-TrainingBackbone=MLP, Trained on large model embeddings=true, Protocol=Co-Training2023.1180.1
Deep EnsembleTrained on large model embeddings=true, Protocol=Deep Ensemble2023.1180
DINOv2Backbone=ViT-L, Protocol=Linear2023.1178.1
Semi-ViTBackbone=ViT-L, Protocol=Self-trained2023.1177.3
SimCLRv2Backbone=ResNet152-w2, Protocol=Fine-tuned2023.1174.2
EsViTBackbone=Swin-B, W=14, Protocol=Linear2023.1169.1
SWAVBackbone=RN50-w4, Protocol=Fine-tuned2023.1153.9
MAEBackbone=ViT-L, Protocol=MLP2023.1123.4