Bayesian DeepLab

Reported on 4 benchmarks across 1 task · 2 papers · 2 SOTA

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

Methodology4 results

Anomaly DetectiononFishyscapes
AP· 2018-11-30
48.7
best: 95.96 (RPL+CoroCL)
SOTA
Evaluating Bayesian Deep Learning Methods for Semantic Segmentation arXiv:1811.12709
Anomaly DetectiononFishyscapes
FPR95· 2018-11-30
15.5
best: 21.58 (FlowEneDet)
SOTA
Evaluating Bayesian Deep Learning Methods for Semantic Segmentation arXiv:1811.12709
Anomaly DetectiononFishyscapes L&F
AP· 2019-04-05
9.8
best: 69.8 (cDNP+OE)
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation arXiv:1904.03215
Anomaly DetectiononFishyscapes L&F
FPR95· 2019-04-05
38.5
best: 47.43 (Dirichlet DeepLab)
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation arXiv:1904.03215