DeepViT: Towards Deeper Vision Transformer
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
DeepVit-L* (DeiT training recipe)
#495
Top 1 Accuracy: 83.1%
image-classification-on-imagenet
DeepVit-L
#598
Top 1 Accuracy: 82.2%
Number of params: 55M
Rank counts only results with a code link.