Base (DeiT-T)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2020-12-23
1.2
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2020-12-23
72.2
best: 72.9 (dTPS)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877