Advances, Systems and Applications
Table 1 Three benchmark imagesets used in our experiment
From: Visibility estimation via deep label distribution learning in cloud environment
Dataset | Blurry | Sub-blurry | Sub-clear | Clear |
|---|---|---|---|---|
FROSI | 41.8% | 22.1% | 10.9% | 25.2% |
FRIDA | 11.4% | 44.5% | 33.7% | 10.4% |
RMID | 10.8% | 23.4% | 34.0% | 31.8% |