DiscreteViT (Im21k)

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Methodology1 result

Domain AdaptationonImageNet-C
mean Corruption Error (mCE)· uses extra data· 2021-11-20
38.74
best: 22 (EfficientNet-L2+RPL)
Discrete Representations Strengthen Vision Transformer Robustness arXiv:2111.10493

Computer Vision1 result

Domain GeneralizationonImageNet-C
mean Corruption Error (mCE)· uses extra data· 2021-11-20
38.74
best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
Discrete Representations Strengthen Vision Transformer Robustness arXiv:2111.10493