Multi-label Few-Shot Classification on Pascal 5^i (cross-validation folds S0-S3)
86.6Exact Ratio Acc (%) (S0)HSNet
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| HSNetN-way=1-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 86.6 | 84.8 | 76.9 | 86.3 | 83.7 | |
| ASNet_wN-way=1-way, K-shot=1-shot, Supervision=Weak labels (class tags), Backbone=ResNet-50, Framework=iFSL2022.03 | 86.4 | 86.3 | 70.9 | 84.5 | 82 | |
| ASNetN-way=1-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 84.9 | 89.6 | 79 | 86.2 | 84.9 | |
| ASNet_wN-way=2-way, K-shot=1-shot, Supervision=Weak labels (class tags), Backbone=ResNet-50, Framework=iFSL2022.03 | 71.6 | 72.4 | 46.4 | 68 | 64.6 | |
| PANetN-way=1-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 69.9 | 67.7 | 68.8 | 69.4 | 69 | |
| PFENetN-way=1-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 69.8 | 82.4 | 68.1 | 77.9 | 74.6 | |
| ASNetN-way=2-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 68.5 | 76.2 | 58.6 | 70 | 68.3 | |
| HSNetN-way=2-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 68 | 73.2 | 57 | 70.9 | 67.3 | |
| PANetN-way=2-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 56.2 | 47.5 | 44.6 | 55.4 | 50.9 | |
| PFENetN-way=2-way, K-shot=1-shot, Supervision=Strong labels, Backbone=ResNet-50, Framework=iFSL2022.03 | 22.5 | 61.7 | 40.3 | 39.5 | 41 |