Image Classification On Inaturalist 2019

评估指标

Top-1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	Top-1 Accuracy	Paper Title
LeViT-192	70.8	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
CeiT-S	78.9	Incorporating Convolution Designs into Visual Transformers
CeiT-S (384 finetune resolution)	82.7	Incorporating Convolution Designs into Visual Transformers
ResNet50 (A2)	75.0	ResNet strikes back: An improved training procedure in timm
RDNet-T (224 res, IN-1K pretrained)	81.2	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
Conviformer-B	82.85	Conviformers: Convolutionally guided Vision Transformer
MixMIM-L	83.9	MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
MAE (ViT-H, 448)	88.3	Masked Autoencoders Are Scalable Vision Learners
RDNet-S (224 res, IN-1K pretrained)	82.9	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
Hiera-H (448px)	88.5	Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
RDNet-L (224 res, IN-1K pretrained)	83.7	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
LeViT-256	72.3	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-128	68.4	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
CeiT-T	72.8	Incorporating Convolution Designs into Visual Transformers
ResMLP-12	71.0	ResMLP: Feedforward networks for image classification with data-efficient training
CeiT-T (384 finetune resolution)	77.9	Incorporating Convolution Designs into Visual Transformers
RDNet-B (224 res, IN-1K pretrained)	83.5	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
LeViT-384	74.3	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-128S	66.5	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
CaiT-M-36 U 224	81.8	Going deeper with Image Transformers

0 of 22 row(s) selected.