E2E-3M

Reported on 5 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 Vision5 results

Image ClassificationonSurrey ASL
Accuracy (%)· 2020-07-30
94.9
SOTA
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification arXiv:2007.15161
Image ClassificationoniCassava'19
Top-1 Accuracy· 2020-07-30
0.9368
SOTA
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification arXiv:2007.15161
Image ClassificationonFashion-MNIST
Percentage error· 2020-07-30
4.08
best: 3.64 (PreAct-ResNet18 + FMix)
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification arXiv:2007.15161
Image ClassificationonCIFAR-10
Percentage correct· 2020-07-30
98.52
best: 99.5 (ViT-H/14)
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification arXiv:2007.15161
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2020-07-30
90.27
best: 96.08 (EffNet-L2 (SAM))
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification arXiv:2007.15161