Vision Xformers: Efficient Attention for Image Classification

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10CCN#253Percentage correct: 83.36
image-classification-on-cifar-10CvN#254Percentage correct: 83.26
image-classification-on-cifar-10LeViP#261Percentage correct: 79.50
image-classification-on-cifar-10Hybrid ViT+RoPE#263Percentage correct: 76.9
image-classification-on-cifar-10Hybrid Vision Nystromformer (ViN)#264Percentage correct: 75.26
image-classification-on-cifar-10Hybrid PiN#266Percentage correct: 74
image-classification-on-cifar-10Vision Nystromformer (ViN)#269Percentage correct: 65.06

Rank counts only results with a code link.