Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies. (arXiv:2206.08462v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08462

Human vision involves parsing and representing objects and scenes using
structured representations based on part-whole hierarchies. Computer vision and
machine learning researchers have recently sought to emulate this capability
using capsule networks, reference frames and active predictive coding, but a
generative model formulation has been lacking. We introduce Recursive Neural
Programs (RNPs), which, to our knowledge, is the first neural generative model
to address the part-whole hierarchy learning problem. RNPs model images as
hierarchical trees of probabilistic sensory-motor programs that …

arxiv cv image learning neural part recursive