Semi-Supervised Few-Shot Classification on tieredImagenet (test)
83.691-Shot AccuracyEPNetSSL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| EPNetSSLBackbone=WRN-28-10, Number of unlabeled samples=1002020.03 | 83.69 | 89.34 | |
| --NetSSLBackbone=WRN-28-10, Number of unlabeled samples=1002020.03 | 82.03 | 88.2 | |
| EPNetSSLBackbone=RESNET-12, Number of unlabeled samples=1002020.03 | 81.79 | 88.45 | |
| --NetSSLBackbone=RESNET-12, Number of unlabeled samples=1002020.03 | 80.26 | 88.06 | |
| EPNetBackbone=WRN-28-10, Number of unlabeled samples=1002020.03 | 78.5 | 88.36 | |
| LSTBackbone=RESNET-12, Number of unlabeled samples=1002020.03 | 77.7 | 85.2 | |
| EPNetBackbone=RESNET-12, Number of unlabeled samples=1002020.03 | 76.53 | 87.32 | |
| EPNetSSLBackbone=CONV-4, Number of unlabeled samples=1002020.03 | 66.63 | 75.7 | |
| --NetSSLBackbone=CONV-4, Number of unlabeled samples=1002020.03 | 65.01 | 74.24 | |
| EPNetBackbone=CONV-4, Number of unlabeled samples=1002020.03 | 59.97 | 73.91 | |
| TPNSSLBackbone=CONV-4, Number of unlabeled samples=1002020.03 | 55.74 | 71.01 |