Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation

Benchmark Model Rank Results
anomaly-detection-on-fishyscapes-1SML#7AP: 53.11FPR95: 19.64
anomaly-detection-on-fishyscapes-l-fSML#9AP: 36.55FPR95: 14.53
anomaly-detection-on-lost-and-foundSML#4AP: 25.89FPR: 44.48
anomaly-detection-on-road-anomalySML#8AP: 25.82FPR95: 49.74
semantic-segmentation-on-cityscapes-valSML#49mIoU: 80.33