ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
ViTAE-H + MAE (448)
#42
Top 1 Accuracy: 88.5%
Number of params: 644M
image-classification-on-imagenet-real
ViTAE-H (MAE, 512)
#2
Accuracy: 91.2%
Params: 644M
Rank counts only results with a code link.