Measuring uncertainty in human visual segmentation
Fig 2
Equivalence of loss functions and effects of regularization.
Top left: value of the BCE loss when we optimize for BCE (dashed lines) or for SE (continuous lines). Top center: same but for SE loss. Bottom left: value of the reconstruction MAE. In all panels, the shaded areas represent 95% bootstrap error bars over 1000 simulations. Right: ground truth (GT) probabilistic maps and reconstructed probabilistic maps for each objective function indicated in the legend. The mention “10 Reg.” means that we use regularization with λ = 10.