MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10WRN-28-10#72Percentage correct: 97.73
image-classification-on-cifar-100WRN-28-10 * 3#50Percentage correct: 86.81
image-classification-on-cifar-100WRN-28-10#58Percentage correct: 85.77
image-classification-on-tiny-imagenet-classificationPreActResNet-18-3#14Validation Acc: 70.24%

Rank counts only results with a code link.