ResMLP-24

Reported on 6 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision6 results

Image ClassificationoniNaturalist 2018
Top-1 Accuracy· 2021-05-07
64.3
best: 94.6 (OmniVec2)
SOTA
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404
Image ClassificationonCertificate Verification
Percentage correct· 2021-05-07
98.7
SOTA
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404
Image ClassificationonCertificate Verification
Top-1 Accuracy· 2021-05-07
98.7
SOTA
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404
Image ClassificationonStanford Cars
Accuracy· 2021-05-07
89.5
best: 96.868 (efficient adaptive ensembling)
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404
Image ClassificationoniNaturalist 2019
Top-1 Accuracy· 2021-05-07
72.5
best: 88.5 (Hiera-H (448px))
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-05-07
89.5
best: 96.08 (EffNet-L2 (SAM))
ResMLP: Feedforward networks for image classification with data-efficient training arXiv:2105.03404