EsViT (Swin-B)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Image ClassificationonImageNet
Top 1 Accuracy· 2021-06-17
81.3
best: 88.3 (Unicom (ViT-L/14@336px) (Finetuned))
Efficient Self-supervised Vision Transformers for Representation Learning arXiv:2106.09785
Image ClassificationonImageNet
Top 5 Accuracy· 2021-06-17
95.5
best: 99.02 (Florence-CoSwin-H)
Efficient Self-supervised Vision Transformers for Representation Learning arXiv:2106.09785