Bayesian deep learning for affordance segmentation in images
Lorenzo Mur-Labadia,Ruben Martinez-Cantin,Jose J. Guerrero,Lorenzo Mur-Labadia,Ruben Martinez-Cantin,Jose J. Guerrero
Affordances are a fundamental concept in robotics since they relate available actions for an agent depending on its sensory-motor capabilities and the environment. We present a novel Bayesian deep network to detect affordances in images, at the same time that we quantify the distribution of the aleatoric and epistemic variance at the spatial level. We adapt the Mask-RCNN architecture to learn a pr...
