Anomaly Detection On Fishyscapes 1
评估指标
AP
FPR95
评测结果
各个模型在此基准测试上的表现结果
模型名称 | AP | FPR95 | Paper Title | Repository |
|---|---|---|---|---|
| Mask2Anomaly | 95.20 | 0.82 | Unmasking Anomalies in Road-Scene Segmentation | - |
| Bayesian DeepLab | 48.7 | 15.5 | Evaluating Bayesian Deep Learning Methods for Semantic Segmentation | - |
| PEBAL | 92.38 | 1.73 | Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes | - |
| DenseHybrid | 72.3 | 5.5 | DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition | - |
| RPL+CoroCL | 95.96 | 0.52 | Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation | - |
| Synboost | 72.59 | 18.75 | Pixel-wise Anomaly Detection in Complex Driving Scenes | - |
| FlowEneDet | 67.8 | 21.58 | Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow | - |
| SML | 53.11 | 19.64 | Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation | - |
0 of 8 row(s) selected.