ReNet

Reported on 3 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 Vision3 results

Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2015-05-03
87.7
best: 99.5 (ViT-H/14)
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks arXiv:1505.00393
Image ClassificationonMNIST
Percentage error· 2015-05-03
0.5
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks arXiv:1505.00393
Image ClassificationonSVHN
Percentage error· 2015-05-03
2.4
best: 1 (E2E-M3)
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks arXiv:1505.00393