Dirichlet DeepLab

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Anomaly DetectiononFishyscapes L&F
AP· uses extra data· 2019-04-05
34.28
best: 69.8 (cDNP+OE)
SOTA
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation arXiv:1904.03215
Anomaly DetectiononFishyscapes L&F
FPR95· uses extra data· 2019-04-05
47.43
SOTA
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation arXiv:1904.03215