Domain Generalization on Office-Home
96.91Overall Average AccuracyODG-CLIP
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ODG-CLIPBackbone Category=CLIP-based2024.03 | 96.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StyLIPBackbone Category=CLIP-based2024.03 | 85.94 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LASPBackbone Category=CLIP-based2024.03 | 84.13 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PromptSRCBackbone Category=CLIP-based2024.03 | 83.89 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaPLeBackbone Category=CLIP-based2024.03 | 83.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CoOpBackbone Category=CLIP-based2024.03 | 81.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CoCoOpBackbone Category=CLIP-based2024.03 | 81.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPBackbone Category=CLIP-based2024.03 | 78.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EoABackbone Category=CNN2024.03 | 72.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SWADBackbone Category=CNN2024.03 | 70.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DandelionNetBackbone Category=CNN2024.03 | 70.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Shape-Biased FrameworkBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 68.8 | 56.6 | 73.5 | 80.7 | 61.7 | 70.2 | 74.38 | 60.1 | 52.7 | 81.1 | 73.2 | 59.7 | 81.9 | — | — | — | — | |
| STEAMBackbone=ResNet-182021.12 | 66.8 | — | — | — | — | — | — | — | — | — | — | — | — | 62.1 | 52.3 | 75.4 | 77.5 | |
| L2A-OTBackbone=ResNet-182021.12 | 65.6 | — | — | — | — | — | — | — | — | — | — | — | — | 60.6 | 50.1 | 74.8 | 77 | |
| MixStyleBackbone=ResNet-182021.12 | 65.5 | — | — | — | — | — | — | — | — | — | — | — | — | 58.7 | 53.4 | 74.2 | 75.9 | |
| DWT-MECBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 65.4 | 54.7 | 72.3 | 77.2 | 56.9 | 68.5 | 69.8 | 54.8 | 47.9 | 78.1 | 68.6 | 54.9 | 81.2 | — | — | — | — | |
| CCSABackbone=ResNet-182021.12 | 64.9 | — | — | — | — | — | — | — | — | — | — | — | — | 59.9 | 49.9 | 74.1 | 75.7 | |
| Core-tuningPre-training=MoCo-v2, Fine-tuning=ours2021.02 | 64.85 | — | — | — | — | — | — | — | — | — | — | — | — | 58.7 | 52.43 | 72.89 | 75.36 | |
| VanillaBackbone=ResNet-182021.12 | 64.7 | — | — | — | — | — | — | — | — | — | — | — | — | 58.9 | 49.4 | 74.3 | 76.2 | |
| CrossGradBackbone=ResNet-182021.12 | 64.4 | — | — | — | — | — | — | — | — | — | — | — | — | 58.4 | 49.4 | 73.9 | 75.8 | |
| DWTBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 64.3 | 50.8 | 72 | 75.8 | 58.9 | 65.6 | 60.2 | 57.2 | 49.5 | 78.3 | 70.1 | 55.3 | 78.2 | — | — | — | — | |
| CEPre-training=Supervised, Fine-tuning=CE2021.02 | 63.82 | — | — | — | — | — | — | — | — | — | — | — | — | 56.08 | 50.83 | 72.49 | 75.21 | |
| CE-ConPre-training=MoCo-v2, Fine-tuning=CE-Con2021.02 | 63.15 | — | — | — | — | — | — | — | — | — | — | — | — | 55.87 | 50.23 | 71.51 | 74.99 | |
| CDAN-MBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 62.8 | 50.6 | 65.9 | 73.4 | 55.7 | 62.7 | 64.2 | 51.8 | 49.1 | 74.5 | 68.2 | 56.9 | 80.7 | — | — | — | — | |
| MMD-AAEBackbone=ResNet-182021.12 | 62.7 | — | — | — | — | — | — | — | — | — | — | — | — | 56.5 | 47.3 | 72.1 | 74.8 | |
| JiGenBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 62.5 | 48.6 | 66.6 | 77.4 | 53.9 | 60.1 | 64.9 | 51.7 | 47.7 | 78.1 | 70.7 | 51.4 | 79.3 | — | — | — | — | |
| CDAN-RMBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 61.6 | 49.2 | 64.8 | 72.9 | 53.8 | 63.9 | 62.9 | 49.8 | 48.8 | 71.5 | 65.8 | 56.4 | 79.2 | — | — | — | — | |
| SEBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 61.5 | 48.8 | 61.8 | 72.8 | 54.1 | 63.2 | 65.1 | 50.6 | 49.2 | 72.3 | 66.1 | 55.9 | 78.7 | — | — | — | — | |
| JiGenBackbone=ResNet-182021.12 | 61.2 | — | — | — | — | — | — | — | — | — | — | — | — | 53 | 47.5 | 71.5 | 72.8 | |
| JANBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 58.3 | 45.9 | 61.2 | 70.9 | 50.4 | 59.7 | 61 | 45.8 | 43.4 | 70.3 | 63.9 | 52.4 | 76.8 | — | — | — | — | |
| CEPre-training=MoCo-v2, Fine-tuning=CE2021.02 | 58.18 | — | — | — | — | — | — | — | — | — | — | — | — | 50.31 | 48.91 | 64.72 | 68.76 | |
| DANNBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 57.6 | 45.6 | 59.3 | 70.1 | 47 | 58.5 | 60.9 | 46.1 | 43.7 | 68.5 | 63.2 | 51.8 | 76.8 | — | — | — | — | |
| DANBackbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 56.3 | 43.6 | 57 | 67.9 | 45.8 | 56.5 | 60.4 | 44 | 43.6 | 67.7 | 63.1 | 51.5 | 74.3 | — | — | — | — | |
| ResNet-50Backbone=ResNet-50, Evaluation Protocol=Single-source domain generalization2019.09 | 46.1 | 34.9 | 50 | 58 | 37.4 | 41.9 | 46.2 | 38.5 | 31.2 | 60.4 | 53.9 | 41.2 | 59.9 | — | — | — | — |