Domain Generalization using Pretrained Models without Fine-tuning

Open paper
Benchmark Model Rank Results
domain-generalization-on-domainnetSEDGE–Average Accuracy: 46.3
domain-generalization-on-domainnetSEDGE+–Average Accuracy: 54.7
domain-generalization-on-office-homeSEDGE–Average Accuracy: 79.9
domain-generalization-on-office-homeSEDGE+–Average Accuracy: 80.7
domain-generalization-on-pacs-2SEDGE–Average Accuracy: 84.1
domain-generalization-on-pacs-2SEDGE+–Average Accuracy: 96.1
domain-generalization-on-terraincognitaSEDGE–Average Accuracy: 56.8
domain-generalization-on-terraincognitaSEDGE+–Average Accuracy: 56.8
domain-generalization-on-vlcsSEDGE–Average Accuracy: 79.8
domain-generalization-on-vlcsSEDGE+–Average Accuracy: 82.2

Rank counts only results with a code link.