SpeedyLiteVision Network

Reported on 3 benchmarks across 1 task

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

Computer Vision3 results

Image ClassificationonFashion-MNIST
Accuracy
91.6
best: 99.06 (pFedBreD_ns_mg)
Image ClassificationonFashion-MNIST
Percentage error
8.4
best: 3.64 (PreAct-ResNet18 + FMix)
Image ClassificationonFashion-MNIST
Trainable Parameters
35978
best: 892362 (R-ExplaiNet-26)