ViT-B/16 (ANN-1.3B)

Reported on 1 benchmark 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 Vision1 result

Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2021-08-12
50.7
best: 82.7 (CoCa)
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations arXiv:2108.05887