Image Classification on STL to CIFAR standard (test)
90.44AccuracySupTgt
Evaluation Results
| Method | Links | |
|---|---|---|
| SupTgtTraining Protocol=Train on Target, Augmentation Type=TFA2017.06 | 90.44 | |
| Target only (baseline)training=Target domain only2019.10 | 90.4 | |
| SupTgtTraining Protocol=Train on Target, Augmentation Type=TF2017.06 | 89.83 | |
| SupTgtTraining Protocol=Train on Target, Augmentation Type=minimal2017.06 | 88.86 | |
| Co-DA2019.10 | 76.4 | |
| Co-DA+DIRT-T2019.10 | 76.3 | |
| DIRT-T2019.10 | 75.5 | |
| DIRT-T2019.09 | 75.3 | |
| Mean TeacherTraining Protocol=Unsupervised Domain Adaptation, Augmentation Type=TF, Confidence Thresholding=true2017.06 | 74.24 | |
| SE*Protocol=MT+CT+TF2019.10 | 74.2 | |
| Proposed MethodTask=Rotation, Location, Flip2019.09 | 74 | |
| VADA2019.09 | 73.5 | |
| VADA2019.10 | 73.5 | |
| DIRT-TBackbone=Instance Normalization2019.09 | 73.3 | |
| DTA2019.10 | 72.8 | |
| Mean TeacherTraining Protocol=Unsupervised Domain Adaptation, Augmentation Type=minimal, Confidence Thresholding=true2017.06 | 71.65 | |
| VADABackbone=Instance Normalization2019.09 | 71.4 | |
| Mean TeacherTraining Protocol=Unsupervised Domain Adaptation, Augmentation Type=TFA, Confidence Thresholding=true2017.06 | 69.86 | |
| Proposed MethodTask=Rotation2019.09 | 65.6 | |
| Π-Model2019.09 | 64.2 | |
| Source only (VADA & DIRT-T)mode=source only2019.09 | 63.6 | |
| Source only (VADA & DIRT-T)mode=source only, Backbone=Instance Normalization2019.09 | 62.6 | |
| Source only (baseline)training=Source domain only2019.10 | 60.1 | |
| SupSrcTraining Protocol=Train on Source, Augmentation Type=TFA2017.06 | 59.38 | |
| SupSrcTraining Protocol=Train on Source, Augmentation Type=TF2017.06 | 59.06 | |
| DRCN2019.09 | 58.7 | |
| DCRNTraining Protocol=Unsupervised Domain Adaptation2017.06 | 58.65 | |
| RevGradTraining Protocol=Unsupervised Domain Adaptation2017.06 | 56.91 | |
| S+F2021.06 | 56.9 | |
| TOHAN2021.06 | 56.6 | |
| TOHAN2021.06 | 56.6 | |
| Source only (Our method)mode=source only2019.09 | 56.1 | |
| T+F2021.06 | 55.8 | |
| FT2021.06 | 54.3 | |
| SHOT2021.06 | 53.9 | |
| dkdHTL2021.06 | 52.4 | |
| SupSrcTraining Protocol=Train on Source, Augmentation Type=minimal2017.06 | 51.88 | |
| WA2021.06 | 51.8 | |
| Mean TeacherTraining Protocol=Unsupervised Domain Adaptation, Augmentation Type=TF2017.06 | 18.3 |