DVT (T2T-ViT-24)

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 ClassificationonCIFAR-10
Percentage correct· 2021-05-31
98.53
best: 99.5 (ViT-H/14)
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition arXiv:2105.15075
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-05-31
89.63
best: 96.08 (EffNet-L2 (SAM))
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition arXiv:2105.15075