Open World Semi Supervised Learning On 1
评估指标
All accuracy (50% Labeled)
Novel accuracy (50% 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 (50% Labeled) | Novel accuracy (50% Labeled) | Seen accuracy (50% Labeled) | Paper Title | Repository |
|---|---|---|---|---|---|
| GCD (ViT-B-16) | 74.1 | 66.3 | 89.8 | Generalized Category Discovery | |
| SimGCD (ViT-B-16) | 83.6 | 79.1 | 92.4 | Parametric Classification for Generalized Category Discovery: A Baseline Study | |
| TRSSL (ResNet-50) | - | - | - | Towards Realistic Semi-Supervised Learning | |
| OpenLDN (ResNet-50) | 79.1 | 68.6 | 89.6 | OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning | |
| ORCA (ResNet-50) | 77.8 | 72.1 | 89.1 | Open-World Semi-Supervised Learning |
0 of 5 row(s) selected.