Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Open paper
Benchmark Model Rank Results
domain-generalization-on-domainnetMIRO (RegNetY-16GF, SWAD)#10Average Accuracy: 60.7
domain-generalization-on-domainnetMIRO (ResNet-50, SWAD)#24Average Accuracy: 47.0
domain-generalization-on-office-homeMIRO (RegNetY-16GF, SWAD)#11Average Accuracy: 83.3
domain-generalization-on-office-homeMIRO (ResNet-50, SWAD)#21Average Accuracy: 72.4
domain-generalization-on-pacs-2MIRO (RegNetY-16GF, SWAD)#9Average Accuracy: 96.8
domain-generalization-on-pacs-2MIRO (ResNet-50, SWAD)#25Average Accuracy: 88.4
domain-generalization-on-terraincognitaMIRO (RegNetY-16GF, SWAD)#3Average Accuracy: 64.3
domain-generalization-on-terraincognitaMIRO (ResNet-50, SWAD)#12Average Accuracy: 52.9
domain-generalization-on-vlcsMIRO (RegNetY-16GF, SWAD)#13Average Accuracy: 81.7
domain-generalization-on-vlcsMIRO (ResNet-50, SWAD)#20Average Accuracy: 79.6

Rank counts only results with a code link.