MLP-Mixer

Reported on 2 benchmarks across 1 task · 2 papers

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

Computer Vision2 results

Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2021-11-30
25.9
best: 82.7 (CoCa)
Pyramid Adversarial Training Improves ViT Performance arXiv:2111.15121
Image ClassificationonOmniBenchmark
Average Top-1 Accuracy· 2021-05-04
32.2
best: 47.6 (NOAH-ViTB/16)
MLP-Mixer: An all-MLP Architecture for Vision arXiv:2105.01601