Image Classification On Stanford Cars

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
efficient adaptive ensembling	96.879	Efficient Adaptive Ensembling for Image Classification	-
TResNet-L-V2	96.32	ImageNet-21K Pretraining for the Masses
EfficientNetV2-L	95.1	EfficientNetV2: Smaller Models and Faster Training
EfficientNetV2-M	94.6	EfficientNetV2: Smaller Models and Faster Training
CaiT-M-36 U 224	94.2	-	-
CeiT-S (384 finetune resolution)	94.1	Incorporating Convolution Designs into Visual Transformers
ImageNet + iNat on WS-DAN	94.1	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	-
EfficientNetV2-S	93.8	EfficientNetV2: Smaller Models and Faster Training
ViT-B/16 (RPE w/ GAB)	93.743	Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
CeiT-S	93.2	Incorporating Convolution Designs into Visual Transformers
GFNet-H-B	93.2	Global Filter Networks for Image Classification
CeiT-T (384 finetune resolution)	93	Incorporating Convolution Designs into Visual Transformers
TransBoost-ResNet50	90.80%	TransBoost: Improving the Best ImageNet Performance using Deep Transduction
CeiT-T	90.5	Incorporating Convolution Designs into Visual Transformers
LeViT-192	89.8	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
ResMLP-24	89.5	ResMLP: Feedforward networks for image classification with data-efficient training
LeViT-384	89.3	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-128	88.6	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-128S	88.4	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-256	88.2	LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference

0 of 24 row(s) selected.