VGG8B(2x) + LocalLearning + CO

Reported on 3 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 Vision3 results

Image ClassificationonKuzushiji-MNIST
Accuracy· 2019-01-20
99.01
best: 99.35 (KMNIST-Tiny)
SOTA
Training Neural Networks with Local Error Signals arXiv:1901.06656
Image ClassificationonKuzushiji-MNIST
Error· 2019-01-20
0.99
best: 0.85 (VGG-5 (Spinal FC))
SOTA
Training Neural Networks with Local Error Signals arXiv:1901.06656
Image ClassificationonFashion-MNIST
Percentage error· 2019-01-20
4.14
best: 3.64 (PreAct-ResNet18 + FMix)
Training Neural Networks with Local Error Signals arXiv:1901.06656