Base (DeiT-S)

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-S)
GFLOPs· 2020-12-23
4.6
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2020-12-23
79.8
best: 80.1 (MCTF ($r=16$))
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877