Few-shot Image Classification on ChestX CDFSL (test)
28.5Accuracy (5-way 5-shot)Ours_trans
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ours_transLearning set-up=Transductive, Embedding network=Mini80_SSL2019.11 | 28.5 | 33.79 | 38.78 | — | |
| ProtoTransferUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 26.71 | 33.82 | 39.35 | — | |
| ProtoTransferUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 26.71 | 33.82 | 39.35 | — | |
| Pre+Mean-CentroidUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 26.31 | 30.41 | 34.68 | — | |
| Pre+Mean-CentroidUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 26.31 | 30.41 | 34.68 | — | |
| CrossLearning set-up=Transductive2019.11 | 26.09 | 31.01 | 36.79 | — | |
| Pre+LinearUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 25.97 | 31.32 | 35.49 | — | |
| Pre+LinearUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 25.97 | 31.32 | 35.49 | — | |
| UMTRA-ProtoTuneUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 25 | 30.41 | 35.63 | — | |
| UMTRA-ProtoTuneUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 25 | 30.41 | 35.63 | — | |
| UMTRA-ProtoNetUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 24.94 | 28.04 | 29.88 | — | |
| UMTRA-ProtoNetUnSup=true, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 24.94 | 28.04 | 29.88 | — | |
| GNN + LRPTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.53 | — | — | 22.11 | |
| RelationNet + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.43 | — | — | 22.14 | |
| GNN + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.32 | — | — | 22.1 | |
| RelationNet + LRPTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.28 | — | — | 22.11 | |
| GNN + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.28 | — | — | 22 | |
| RelationNetTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 24.07 | — | — | 21.95 | |
| ProtoNetUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 24.05 | 28.21 | 29.32 | — | |
| ProtoNetUnSup=false, Backbone=ResNet-10, Training Dataset=mini-ImageNet2020.06 | 24.05 | 28.21 | 29.32 | — | |
| RelationNet + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 23.95 | — | — | 21.79 | |
| GNNTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 23.87 | — | — | 21.94 | |
| TPN + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 23.6 | — | — | 21.67 | |
| TPNTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 22.17 | — | — | 21.05 | |
| TPN + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04 | 21.22 | — | — | 20.46 |