Skip to main content
Advertisement

< Back to Article

Measuring uncertainty in human visual segmentation

Fig 4

Accurate inference of segmentation maps from limited data.

Left : the MAE between reconstructed maps and ground truth (GT) as a function of the number of blocks (with and without regularization, light and dark gray respectively). Shaded areas represent 95% bootstrap error bars. Top–Right: ground truth maps. Center–Right: reconstructed maps without regularization from 1 block (left) and 128 blocks (right). Bottom–Right: same as Center–Right but with regularization. The mention “10 Reg.” means that we use regularization with λ = 10.

Fig 4

doi: https://doi.org/10.1371/journal.pcbi.1011483.g004