HyperAI

Image Classification On Stanford Cars

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
ResMLP-1284.6ResMLP: Feedforward networks for image classification with data-efficient training
ViT-M/16 (RPE w/ GAB)83.89Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
CeiT-S93.2Incorporating Convolution Designs into Visual Transformers
TransBoost-ResNet5090.80%TransBoost: Improving the Best ImageNet Performance using Deep Transduction
ResMLP-2489.5ResMLP: Feedforward networks for image classification with data-efficient training
CeiT-S (384 finetune resolution)94.1Incorporating Convolution Designs into Visual Transformers
LeViT-128S88.4LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-25688.2LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
LeViT-38489.3LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
EfficientNetV2-M94.6EfficientNetV2: Smaller Models and Faster Training
NNCLR67.1With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
GFNet-H-B93.2Global Filter Networks for Image Classification
EfficientNetV2-S93.8EfficientNetV2: Smaller Models and Faster Training
CeiT-T90.5Incorporating Convolution Designs into Visual Transformers
SE-ResNet-101 (SAP)85.812Stochastic Subsampling With Average Pooling-
LeViT-12888.6LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
EfficientNetV2-L95.1EfficientNetV2: Smaller Models and Faster Training
ImageNet + iNat on WS-DAN94.1Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization-
CaiT-M-36 U 22494.2Going deeper with Image Transformers
TResNet-L-V296.32ImageNet-21K Pretraining for the Masses-
0 of 24 row(s) selected.