Open World Semi Supervised Learning On Cifar
评估指标
All accuracy (10% Labeled)
All accuracy (50% Labeled)
Novel accuracy (10% Labeled)
Novel accuracy (50% Labeled)
Seen accuracy (10% Labeled)
Seen accuracy (50% Labeled)
评测结果
各个模型在此基准测试上的表现结果
模型名称 | All accuracy (10% Labeled) | All accuracy (50% Labeled) | Novel accuracy (10% Labeled) | Novel accuracy (50% Labeled) | Seen accuracy (10% Labeled) | Seen accuracy (50% Labeled) | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| OpenLDN (ResNet-18) | 92.8 | 95.4 | 93.2 | 95.1 | 92.4 | 95.7 | OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning | |
| GCD (ViT-B-16) | - | 91.5 | - | 88.2 | - | 97.9 | Generalized Category Discovery | |
| ORCA (ResNet-18) | 84.1 | 89.7 | 85.5 | 90.4 | 82.8 | 88.2 | Open-World Semi-Supervised Learning | |
| TRSSL (ResNet-18) | 92.2 | - | 89.6 | - | 94.9 | - | Towards Realistic Semi-Supervised Learning | |
| SimGCD (ViT-B-16) | - | 97.0 | - | 98.5 | - | 93.9 | Parametric Classification for Generalized Category Discovery: A Baseline Study |
0 of 5 row(s) selected.