Classification on VisDA 2017 (val)
92.8Mean AccuracyMIC (SDAT)
Evaluation results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MIC (SDAT)Backbone=ViT2022.12 | 92.8 | 99 | 93.3 | 86.5 | 87.6 | 98.9 | 99 | 97.2 | 89.8 | 98.9 | 98.9 | 96.5 | 68 | — | |
| SDATBackbone=ViT2022.12 | 89.8 | 98.4 | 90.9 | 85.4 | 82.1 | 98.5 | 97.6 | 96.3 | 86.1 | 96.2 | 96.7 | 92.9 | 56.8 | — | |
| CDTransBackbone=ViT2022.12 | 88.4 | 97.1 | 90.5 | 82.4 | 77.5 | 96.6 | 96.1 | 93.6 | 88.6 | 97.9 | 86.9 | 90.3 | 62.8 | — | |
| SDAT w/ MAEBackbone=ViT2022.12 | 88.4 | 97.1 | 88.4 | 80.9 | 75.3 | 95.4 | 97.9 | 94.3 | 85.5 | 95.8 | 91 | 93 | 65.4 | — | |
| CANBackbone=ResNet-1012019.01 | 87.2 | 97 | 87.2 | 82.5 | 74.3 | 97.8 | 96.2 | 90.8 | 80.7 | 96.6 | 96.3 | 87.5 | 59.9 | — | |
| MIC (SDAT)Backbone=ResNet2022.12 | 86.9 | 96.7 | 88.5 | 84.2 | 74.3 | 96 | 96.3 | 90.2 | 81.2 | 94.3 | 95.4 | 88.9 | 56.6 | — | |
| SEBackbone=ResNet-1012019.01 | 84.3 | 95.9 | 87.4 | 85.2 | 58.6 | 96.2 | 95.7 | 90.6 | 80 | 94.8 | 90.8 | 88.4 | 47.9 | — | |
| SDATBackbone=ResNet2022.12 | 84.3 | 95.8 | 85.5 | 76.9 | 69 | 93.5 | 97.4 | 88.5 | 78.2 | 93.1 | 91.6 | 86.3 | 55.3 | — | |
| intra onlyBackbone=ResNet-1012019.01 | 83.9 | 96.5 | 72.1 | 80.9 | 70.8 | 94.6 | 98 | 91.7 | 84.2 | 90.3 | 89.8 | 89.4 | 47.9 | — | |
| TVTBackbone=ViT2022.12 | 83.9 | 92.9 | 85.6 | 77.5 | 60.5 | 93.6 | 98.2 | 89.3 | 76.4 | 93.6 | 92 | 91.7 | 55.7 | — | |
| CDAN + ParetoDABackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 83.2 | 95.9 | 82.8 | 81.3 | 58.7 | 93.9 | 93.7 | 85.9 | 83 | 91.9 | 92 | 87.1 | 51.8 | — | |
| SEBackbone=ResNet-50, Ensemble=true, Ensemble Size=16 predictions2019.10 | 82.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DANN + ParetoDABackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 82.4 | 95.3 | 82.4 | 82.9 | 56.2 | 92.6 | 95 | 87.1 | 81.1 | 90.2 | 90.8 | 87.8 | 46.7 | — | |
| DTABackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 81.5 | 93.7 | 82.2 | 85.6 | 83.8 | 93 | 81 | 90.7 | 82.1 | 95.1 | 78.1 | 86.4 | 32.1 | — | |
| TPNBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 80.4 | 93.7 | 85.1 | 69.2 | 81.6 | 93.5 | 61.9 | 89.3 | 81.4 | 93.5 | 81.6 | 84.5 | 49.9 | — | |
| MCCBackbone=ResNet2022.12 | 78.8 | 88.1 | 80.3 | 80.5 | 71.5 | 90.1 | 93.2 | 85 | 71.6 | 89.4 | 73.8 | 85 | 36.9 | — | |
| JADABackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 77 | 91.9 | 78 | 81.5 | 68.7 | 90.2 | 84.1 | 84 | 73.6 | 88.2 | 67.2 | 79 | 38 | — | |
| SWDBackbone=ResNet-101, Pre-trained=ImageNet, Evaluation Protocol=Fine-tuning2019.03 | 76.4 | 90.8 | 82.5 | 81.7 | 70.5 | 91.7 | 69.5 | 86.3 | 77.5 | 87.4 | 63.6 | 85.6 | 29.2 | — | |
| DTABackbone=ResNet-50, Ensemble=false2019.10 | 76.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDAN + BSPBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 75.9 | 92.4 | 61 | 81 | 57.5 | 89 | 80.6 | 90.1 | 77 | 84.2 | 77.9 | 82.1 | 38.4 | — | |
| ADRBackbone=ResNet-1012019.01 | 74.8 | 87.8 | 79.5 | 83.7 | 65.3 | 92.3 | 61.8 | 88.9 | 73.2 | 87.8 | 60 | 85.5 | 32.3 | — | |
| CDANBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 73.9 | 85.2 | 66.9 | 83 | 50.8 | 84.2 | 74.9 | 88.1 | 74.5 | 83.4 | 76 | 81.9 | 38 | — | |
| CDANBackbone=ResNet2022.12 | 73.9 | 85.2 | 66.9 | 83 | 50.8 | 84.2 | 74.9 | 88.1 | 74.5 | 83.4 | 76 | 81.9 | 38 | — | |
| DANN + BSPBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 72.1 | 92.2 | 72.5 | 83.8 | 47.5 | 87 | 54 | 86.8 | 72.4 | 80.6 | 66.9 | 84.5 | 37.1 | — | |
| MCDBackbone=ResNet-101, Pre-trained=ImageNet, Evaluation Protocol=Fine-tuning2019.03 | 71.9 | 87 | 60.9 | 83.7 | 64 | 88.9 | 79.6 | 84.7 | 76.9 | 88.6 | 40.3 | 83 | 25.8 | — | |
| MCDBackbone=ResNet-1012019.01 | 71.9 | 87 | 60.9 | 83.7 | 64 | 88.9 | 79.6 | 84.7 | 76.9 | 88.6 | 40.3 | 83 | 25.8 | — | |
| MCDBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 71.9 | 87 | 60.9 | 83.7 | 64 | 88.9 | 79.6 | 84.7 | 76.9 | 88.6 | 40.3 | 83 | 25.8 | — | |
| CDAN-EBackbone=ResNet-50, Ensemble=false2019.10 | 70 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SimNetBackbone=ResNet-50, Ensemble=false2019.10 | 69.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GTABackbone=ResNet-50, Ensemble=false2019.10 | 69.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| JANBackbone=ResNet-1012019.01 | 65.7 | 75.7 | 18.7 | 82.3 | 86.3 | 70.2 | 56.9 | 80.5 | 53.8 | 92.5 | 32.2 | 84.5 | 54.5 | — | |
| DANBackbone=ResNet-1012019.01 | 62.8 | 68.1 | 15.4 | 76.5 | 87 | 71.1 | 48.9 | 82.3 | 51.5 | 88.7 | 33.2 | 88.9 | 42.2 | — | |
| JAN-ABackbone=ResNet-50, Ensemble=false2019.10 | 61.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MMDBackbone=ResNet-101, Pre-trained=ImageNet, Evaluation Protocol=Fine-tuning2019.03 | 61.1 | 87.1 | 63 | 76.5 | 42 | 90.3 | 42.9 | 85.9 | 53.1 | 49.7 | 36.3 | 85.8 | 20.7 | — | |
| DANBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 61.1 | 87.1 | 63 | 76.5 | 42 | 90.3 | 42.9 | 85.9 | 53.1 | 49.7 | 36.3 | 85.8 | 20.7 | — | |
| DANNBackbone=ResNet-101, Pre-trained=ImageNet, Evaluation Protocol=Fine-tuning2019.03 | 57.4 | 81.9 | 77.7 | 82.8 | 44.3 | 81.2 | 29.5 | 65.1 | 28.6 | 51.9 | 54.6 | 82.8 | 7.8 | — | |
| RevGradBackbone=ResNet-1012019.01 | 57.4 | 81.9 | 77.7 | 82.8 | 44.3 | 81.2 | 29.5 | 65.1 | 28.6 | 51.9 | 54.6 | 82.8 | 7.8 | — | |
| DANNBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 57.4 | 81.9 | 77.7 | 82.8 | 44.3 | 81.2 | 29.5 | 65.1 | 28.6 | 51.9 | 54.6 | 82.8 | 7.8 | — | |
| DANNBackbone=ResNet-50, Ensemble=false2019.10 | 55 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RTNBackbone=ResNet-50, Ensemble=false2019.10 | 53.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DANBackbone=ResNet-50, Ensemble=false2019.10 | 53 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Source onlyBackbone=ResNet-101, Pre-trained=ImageNet, Evaluation Protocol=Fine-tuning2019.03 | 52.4 | 55.1 | 53.3 | 61.9 | 59.1 | 80.6 | 17.9 | 79.7 | 31.2 | 81 | 26.5 | 73.5 | 8.5 | — | |
| ResNetBackbone=ResNet-101, Evaluation protocol=Unsupervised DA2021.12 | 52.4 | 55.1 | 53.3 | 61.9 | 59.1 | 80.6 | 17.9 | 79.7 | 31.2 | 81 | 26.5 | 73.5 | 8.5 | — | |
| Source-finetuneBackbone=ResNet-1012019.01 | 49.4 | 72.3 | 6.1 | 63.4 | 91.7 | 52.7 | 7.9 | 80.1 | 5.6 | 90.1 | 18.5 | 78.1 | 25.9 | — | |
| Source OnlyBackbone=ResNet-50, Ensemble=false2019.10 | 45.6 | — | — | — | — | — | — | — | — | — | — | — | — | — |