Few-shot Image Classification on EuroSat CDFSL (test)
83.44Accuracy (5-way 5-shot)Ours_trans
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Ours_transLearning set-up=Transductive, Embedding network=Mini80_SSL2019.11 | 83.44 | 90.43 | 94.71 | |
| Pre+Mean-CentroidUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 82.21 | 87.62 | 88.24 | |
| CrossLearning set-up=Transductive2019.11 | 81.76 | 87.97 | 92 | |
| Pre+LinearUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 79.08 | 87.64 | 91.34 | |
| ProtoTransferUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 75.62 | 86.8 | 90.46 | |
| UMTRA-ProtoNetUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 74.91 | 80.42 | 82.24 | |
| ProtoNetUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 73.29 | 82.27 | 80.48 | |
| UMTRA-ProtoTuneUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 68.11 | 81.56 | 85.05 |