UniFormer: Unifying Convolution and Self-attention for Visual Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetUniFormer-L (384 res)#155Top 1 Accuracy: 86.3%Number of params: 100MGFLOPs: 39.2
image-classification-on-imagenetUniFormer-L#209Top 1 Accuracy: 85.6%Number of params: 100MGFLOPs: 12.6
image-classification-on-imagenetUniFormer-S#415Top 1 Accuracy: 83.4%Number of params: 22MGFLOPs: 3.6

Rank counts only results with a code link.