SP-ViT: Learning 2D Spatial Priors for Vision Transformers

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetOur SP-ViT-L|384#173Top 1 Accuracy: 86.3%
image-classification-on-imagenetOur SP-ViT-M|384#194Top 1 Accuracy: 86%
image-classification-on-imagenetOur SP-ViT-L#237Top 1 Accuracy: 85.5%
image-classification-on-imagenetSP-ViT-S|384#277Top 1 Accuracy: 85.1%
image-classification-on-imagenetOur SP-ViT-M#296Top 1 Accuracy: 84.9%
image-classification-on-imagenetOur SP-ViT-S#406Top 1 Accuracy: 83.9%

Rank counts only results with a code link.